Identifying the features learned by neural networks is a core challenge in mechanistic interpretability. Sparse autoencoders (SAEs), which learn a sparse, overcomplete dictionary that reconstructs a network's internal activations, have been used to identify these features. However, SAEs may learn more about the structure of the datatset than the computational structure of the network. There is therefore only indirect reason to believe that the directions found in these dictionaries are functionally important to the network. We propose end-to-end (e2e) sparse dictionary learning, a method for training SAEs that ensures the features learned are functionally important by minimizing the KL divergence between the output distributions of the original model and the model with SAE activations inserted. Compared to standard SAEs, e2e SAEs offer a Pareto improvement: They explain more network performance, require fewer total features, and require fewer simultaneously active features per datapoint, all with no cost to interpretability. We explore geometric and qualitative differences between e2e SAE features and standard SAE features. E2e dictionary learning brings us closer to methods that can explain network behavior concisely and accurately.

Transformers generate valid and diverse chemical structures, but little is known about the mechanisms that enable these models to capture the rules of molecular representation. We present a mechanistic analysis of autoregressive transformers trained on drug-like small molecules to reveal the computational structure underlying their capabilities across multiple levels of abstraction. We identify computational patterns consistent with low-level syntactic parsing and more abstract chemical validity constraints. Using sparse autoencoders (SAEs), we extract feature dictionaries associated with chemically relevant activation patterns. We validate our findings on downstream tasks and find that mechanistic insights can translate to predictive performance in various practical settings.

Current sparse autoencoder (SAE) approaches to neural network interpretability assume that activations can be decomposed through linear superposition into sparse, interpretable features. Despite high reconstruction fidelity, SAEs consistently fail to elimi nate polysemanticity and exhibit pathological behavioral errors. We propose that neural networks encode information in two complementary spaces compressed into the same substrate: feature identity and feature integration. To test this dual encoding hypothe sis, we develop sequential and joint - training architectures to capture identity and integration patterns simultaneously. Joint training achieves 41.3% reconstruction improvement and 51.6% reduction in KL divergence errors. This architecture spontaneously d evelops bimodal feature organization: low squared norm features contributing to integration pathways and the rest contributing directly to the residual. Small nonlinear components (3% of parameters) achieve 16.5% standalone improvements, demonstrating para meter - efficient capture of computational relationships crucial for behavior. Additionally, intervention experiments using 2 2 factorial stimulus designs demonstrated that integration features exhibit selective sensitivity to experimental manipulations and produce systematic behavioral effects on model outputs, including significant nonlinear interaction effects across semantic dimensions. This work provides systematic evidence for (1) dual encoding in neural representations, (2) meaningful non-linearly encod ed feature integrations, and (3) introduces an architectural paradigm shift from post - hoc feature analysis to integrated computational design, establishing foundations for next - generation SAEs.

Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs) by grounding outputs in retrieved evidence, but faithfulness failures, where generations contradict or extend beyond the provided sources, remain a critical challenge. Existing hallucination detection methods for RAG often rely either on large-scale detector training, which requires substantial annotated data, or on querying external LLM judges, which leads to high inference costs. Although some approaches attempt to leverage internal representations of LLMs for hallucination detection, their accuracy remains limited. Motivated by recent advances in mechanistic interpretability, we employ sparse autoencoders (SAEs) to disentangle internal activations, successfully identifying features that are specifically triggered during RAG hallucinations. Building on a systematic pipeline of information-based feature selection and additive feature modeling, we introduce RAGLens, a lightweight hallucination detector that accurately flags unfaithful RAG outputs using LLM internal representations. RAGLens not only achieves superior detection performance compared to existing methods, but also provides interpretable rationales for its decisions, enabling effective post-hoc mitigation of unfaithful RAG. Finally, we justify our design choices and reveal new insights into the distribution of hallucination-related signals within LLMs. The code is available at https://github.com/Teddy-XiongGZ/RAGLens.

Since the advent of machine learning, interpretability has remained a persistent challenge, becoming increasingly urgent as generative models support high-stakes applications in drug and material discovery. Recent advances in large language model (LLM) architectures have yielded chemistry language models (CLMs) with impressive capabilities in molecular property prediction and molecular generation. However, how these models internally represent chemical knowledge remains poorly understood. In this work, we extend sparse autoencoder techniques to uncover and examine interpretable features within CLMs. Applying our methodology to the Foundation Models for Materials (FM4M) SMI-TED chemistry foundation model, we extract semantically meaningful latent features and analyse their activation patterns across diverse molecular datasets. Our findings reveal that these models encode a rich landscape of chemical concepts. We identify correlations between specific latent features and distinct domains of chemical knowledge, including structural motifs, physicochemical properties, and pharmacological drug classes. Our approach provides a generalisable framework for uncovering latent knowledge in chemistry-focused AI systems. This work has implications for both foundational understanding and practical deployment; with the potential to accelerate computational chemistry research.

Prevailing alignment methods induce opaque parameter changes, obscuring what models truly learn. To address this, we introduce Feature Steering with Reinforcement Learning (FSRL), a framework that trains a lightweight adapter to steer model behavior by modulating interpretable sparse features. First, we theoretically demonstrate that this mechanism is expressive enough to approximate the behavioral shifts of post-training processes. We then apply FSRL to preference optimization and perform a causal analysis of the learned policy. Our analysis reveals a crucial insight: the model learns to reward stylistic presentation as a proxy for quality, disproportionately relying on features related to style and formatting over those tied to alignment concepts like honesty. By effectively optimizing the preference objective, FSRL serves as a transparent proxy for observing the alignment process. Overall, FSRL offers an interpretable control interface and a practical way to diagnose how preference optimization pressures manifest at the feature level.

Large language models (LLMs) have achieved remarkable progress, yet their internal mechanisms remain largely opaque, posing a significant challenge to their safe and reliable deployment. Sparse autoencoders (SAEs) have emerged as a promising tool for decomposing LLM representations into more interpretable features, but explaining the features captured by SAEs remains a challenging task. In this work, we propose SAGE (SAE AGentic Explainer), an agent-based framework that recasts feature interpretation from a passive, single-pass generation task into an active, explanation-driven process. SAGE implements a rigorous methodology by systematically formulating multiple explanations for each feature, designing targeted experiments to test them, and iteratively refining explanations based on empirical activation feedback. Experiments on features from SAEs of diverse language models demonstrate that SAGE produces explanations with significantly higher generative and predictive accuracy compared to state-of-the-art baselines.an agent-based framework that recasts feature interpretation from a passive, single-pass generation task into an active, explanationdriven process. SAGE implements a rigorous methodology by systematically formulating multiple explanations for each feature, designing targeted experiments to test them, and iteratively refining explanations based on empirical activation feedback. Experiments on features from SAEs of diverse language models demonstrate that SAGE produces explanations with significantly higher generative and predictive accuracy compared to state-of-the-art baselines.

Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We extend Latent Dirichlet Allocation to embedding spaces and derive the SAE objective as a maximum a posteriori estimator under this model. This view implies SAE features are thematic components rather than steerable directions. Based on this, we introduce SAE-TM, a topic modeling framework that: (1) trains an SAE to learn reusable topic atoms, (2) interprets them as word distributions on downstream data, and (3) merges them into any number of topics without retraining. SAE-TM yields more coherent topics than strong baselines on text and image datasets while maintaining diversity. Finally, we analyze thematic structure in image datasets and trace topic changes over time in Japanese woodblock prints. Our work positions SAEs as effective tools for large-scale thematic analysis across modalities. Code and data will be released upon publication.

Identifying the features learned by neural networks is a core challenge in mechanistic interpretability. Sparse autoencoders (SAEs), which learn a sparse, overcomplete dictionary that reconstructs a network's internal activations, have been used to identify these features. However, SAEs may learn more about the structure of the dataset than the computational structure of the network. There is therefore only indirect reason to believe that the directions found in these dictionaries are functionally important to the network. We propose end-to-end (e2e) sparse dictionary learning, a method for training SAEs that ensures the features learned are functionally important by minimizing the KL divergence between the output distributions of the original model and the model with SAE activations inserted.