{"total":113,"rows":[{"id":"2503.17547","title":"Learning Multi-Level Features with Matryoshka Sparse Autoencoders","created":"2025-03-21","cited_by_count":143,"area":"mechinterp"},{"id":"2411.11296","title":"Steering Language Model Refusal with Sparse Autoencoders","created":"2024-11-18","cited_by_count":95,"area":"mechinterp"},{"id":"2501.18052","title":"SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders","created":"2025-01-29","cited_by_count":80,"area":"diffusion"},{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2512.15674","title":"Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers","created":"2025-12-17","cited_by_count":52,"area":null},{"id":"2601.04480","title":"When Models Manipulate Manifolds: The Geometry of a Counting Task","created":"2026-01-08","cited_by_count":46,"area":null},{"id":"2503.18878","title":"I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39,"area":null},{"id":"2501.09929","title":"Interpretable Steering of Large Language Models with Feature Guided Activation Additions","created":"2025-01-17","cited_by_count":35,"area":"mechinterp"},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"id":"2511.08579","title":"Training Language Models to Explain Their Own Computations","created":"2025-11-11","cited_by_count":30,"area":null},{"id":"2503.07639","title":"Mixture of Experts Made Intrinsically Interpretable","created":"2025-03-05","cited_by_count":24,"area":"moe"},{"id":"2605.11887","title":"Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models","created":"2026-05-12","cited_by_count":21,"area":"mechinterp"},{"id":"2506.15679","title":"Dense SAE Latents Are Features, Not Bugs","created":"2025-06-18","cited_by_count":17,"area":"mechinterp"},{"id":"2505.20254","title":"Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs","created":"2025-05-26","cited_by_count":14,"area":"mechinterp"},{"id":"2506.15963","title":"On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy","created":"2025-06-19","cited_by_count":14,"area":"mechinterp"},{"id":"2602.14111","title":"Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?","created":"2026-02-15","cited_by_count":14,"area":"mechinterp"},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2502.14050","title":"Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder","created":"2025-02-19","cited_by_count":12,"area":"mechinterp"},{"id":"2602.02464","title":"From Directions to Regions: Decomposing Activations in Language Models via Local Geometry","created":"2026-02-02","cited_by_count":12,"area":null},{"id":"2602.14687","title":"SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data","created":"2026-02-16","cited_by_count":11,"area":"synth"},{"id":"2502.18147","title":"Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations","created":"2025-02-25","cited_by_count":10,"area":"mechinterp"},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2506.19382","title":"Measuring and Guiding Monosemanticity","created":"2025-06-24","cited_by_count":10,"area":"mechinterp"},{"id":"2510.03659","title":"Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders","created":"2025-10-04","cited_by_count":10,"area":"mechinterp"},{"id":"2507.23220","title":"Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2509.22033","title":"OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features","created":"2025-09-26","cited_by_count":8,"area":"mechinterp"},{"id":"2512.24063","title":"How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns","created":"2025-12-30","cited_by_count":8,"area":"lr"},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2602.20330","title":"Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking","created":"2026-02-23","cited_by_count":8,"area":"lr"},{"id":"2512.13568","title":"Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerability","created":"2025-12-15","cited_by_count":7,"area":"mechinterp"},{"id":"2602.05859","title":"DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders","created":"2026-02-05","cited_by_count":7,"area":"diffusion"},{"id":"2509.23323","title":"LLM Interpretability with Identifiable Temporal-Instantaneous Representation","created":"2025-09-27","cited_by_count":6,"area":"mechinterp"},{"id":"2512.10805","title":"Interpretable and Steerable Concept Bottleneck Sparse Autoencoders","created":"2025-12-11","cited_by_count":6,"area":"mechinterp"},{"id":"2601.05437","title":"Tracing Moral Foundations in Large Language Models","created":"2026-01-09","cited_by_count":6,"area":"mechinterp"},{"id":"2507.08473","title":"Evaluating SAE interpretability without explanations","created":"2025-07-11","cited_by_count":5,"area":"mechinterp"},{"id":"2507.12990","title":"Teach Old SAEs New Domain Tricks with Boosting","created":"2025-07-17","cited_by_count":5,"area":"mechinterp"},{"id":"2509.12934","title":"The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features","created":"2025-09-16","cited_by_count":5,"area":"alignment"},{"id":"2510.14936","title":"Circuit Insights: Towards Interpretability Beyond Activations","created":"2025-10-16","cited_by_count":5,"area":"mechinterp"},{"id":"2509.23717","title":"Measuring Sparse Autoencoder Feature Sensitivity","created":"2025-09-28","cited_by_count":4,"area":"mechinterp"},{"id":"2605.01555","title":"Automated Interpretability and Feature Discovery in Language Models with Agents","created":"2026-05-02","cited_by_count":4,"area":"agents"},{"id":"2605.07922","title":"Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders","created":"2026-05-08","cited_by_count":4,"area":"mechinterp"},{"id":"2605.18229","title":"Are Sparse Autoencoder Benchmarks Reliable?","created":"2026-05-18","cited_by_count":4,"area":"mechinterp"},{"id":"2606.11722","title":"ICA Lens: Interpreting Language Models Without Training Another Dictionary","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2505.16077","title":"Ensembling Sparse Autoencoders","created":"2025-05-21","cited_by_count":3,"area":"mechinterp"},{"id":"2505.17769","title":"Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models","created":"2025-05-23","cited_by_count":3,"area":"mechinterp"},{"id":"2508.09363","title":"Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders","created":"2025-08-12","cited_by_count":3,"area":"lr"},{"id":"2509.25596","title":"Binary Sparse Coding for Interpretability","created":"2025-09-29","cited_by_count":3,"area":"mechinterp"},{"id":"2510.27413","title":"Atlas-Alignment: Making Interpretability Transferable Across Language Models","created":"2025-10-31","cited_by_count":3,"area":"mechinterp"},{"id":"2602.05184","title":"Towards Worst-Case Guarantees with Scale-Aware Interpretability","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2604.06005","title":"Disentangling MLP Neuron Weights in Vocabulary Space","created":"2026-04-07","cited_by_count":3,"area":"mechinterp"},{"id":"2605.12412","title":"Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2605.14694","title":"The Rate-Distortion-Polysemanticity Tradeoff in SAEs","created":"2026-05-14","cited_by_count":3,"area":"mechinterp"},{"id":"2605.31183","title":"Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines","created":"2026-05-29","cited_by_count":3,"area":"mechinterp"},{"id":"2505.01372","title":"Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii","created":"2025-05-02","cited_by_count":2,"area":"mechinterp"},{"id":"2510.06378","title":"Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.19875","title":"Stream: Scaling up Mechanistic Interpretability to Long Context in LLMs via Sparse Attention","created":"2025-10-22","cited_by_count":2,"area":"mechinterp"},{"id":"2510.26411","title":"MedSAE: Dissecting MedCLIP Representations with Sparse Autoencoders","created":"2025-10-30","cited_by_count":2,"area":"mechinterp"},{"id":"2511.00177","title":"Can SAEs reveal and mitigate racial biases of LLMs in healthcare?","created":"2025-10-31","cited_by_count":2,"area":"mechinterp"},{"id":"2511.06048","title":"Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts","created":"2025-11-08","cited_by_count":2,"area":"mechinterp"},{"id":"2602.04718","title":"Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models","created":"2026-02-04","cited_by_count":2,"area":"mechinterp"},{"id":"2602.11852","title":"Prototype Transformer: Towards Language Model Architectures Interpretable by Design","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2603.20101","title":"Pitfalls in Evaluating Interpretability Agents","created":"2026-03-20","cited_by_count":2,"area":"agents"},{"id":"2603.22593","title":"Language Models Can Explain Visual Features via Steering","created":"2026-03-23","cited_by_count":2,"area":"mechinterp"},{"id":"2605.12874","title":"Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features","created":"2026-05-13","cited_by_count":2,"area":"mechinterp"},{"id":"2605.17204","title":"Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies","created":"2026-05-17","cited_by_count":2,"area":"vla"},{"id":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.21197","title":"Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse Autoencoders","created":"2026-06-19","cited_by_count":2,"area":"mllm"},{"id":"2606.24716","title":"Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations","created":"2026-06-23","cited_by_count":2,"area":"mllm"},{"id":"2505.22572","title":"Fusion Steering: Prompt-Specific Activation Control","created":"2025-05-28","cited_by_count":1,"area":"mechinterp"},{"id":"2508.19780","title":"Interestingness First Classifiers","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2509.20376","title":"ConceptViz: A Visual Analytics Approach for Exploring Concepts in Large Language Models","created":"2025-09-20","cited_by_count":1,"area":"mechinterp"},{"id":"2602.07311","title":"LUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery","created":"2026-02-07","cited_by_count":1,"area":"mechinterp"},{"id":"2602.15278","title":"Visual Persuasion: What Influences Decisions of Vision-Language Models?","created":"2026-02-17","cited_by_count":1,"area":"mllm"},{"id":"2604.03532","title":"LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering","created":"2026-04-04","cited_by_count":1,"area":"mechinterp"},{"id":"2604.16889","title":"Prune, Interpret, Evaluate: A Cross-Layer Transcoder-Native Framework for Efficient Circuit Discovery via Feature Attribution","created":"2026-04-18","cited_by_count":1,"area":"mechinterp"},{"id":"2605.28388","title":"Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.22994","title":"Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?","created":"2026-06-22","cited_by_count":1,"area":"mechinterp"},{"id":"2607.08946","title":"Training, Reading, and Editing Legible Transformers","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2607.16448","title":"Retrieval is Enough: Training-Free Interpretability with a Tool-Using Agent","created":"2026-07-17","cited_by_count":1,"area":"agents"},{"id":"2608.18081","title":"Position: Behavioral Systems Require Behavioral Tests","created":"2026-05-31","cited_by_count":1,"area":"agents"},{"id":"2504.00754","title":"Automated Feature Labeling with Token-Space Gradient Descent","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2505.22255","title":"Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders","created":"2025-05-28","cited_by_count":0,"area":"mechinterp"},{"id":"2506.21468","title":"TopK Language Models","created":"2025-06-26","cited_by_count":0,"area":"mechinterp"},{"id":"2508.14275","title":"Disentangling concept semantics via multilingual averaging in Sparse Autoencoders","created":"2025-08-19","cited_by_count":0,"area":"mechinterp"},{"id":"2508.21324","title":"Distribution-Aware Feature Selection for SAEs","created":"2025-08-29","cited_by_count":0,"area":"mechinterp"},{"id":"2510.01252","title":"GPT and Prejudice: A Sparse Approach to Understanding Learned Representations in Large Language Models","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2602.05096","title":"Visual concept ranking uncovers medical shortcuts used by large multimodal models","created":"2026-02-04","cited_by_count":0,"area":"mllm"},{"id":"2602.10352","title":"Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.17867","title":"ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2602.19115","title":"How Do LLMs Encode Scientific Quality? An Empirical Study Using Monosemantic Features from Sparse Autoencoders","created":"2026-02-22","cited_by_count":0,"area":"mechinterp"},{"id":"2603.23524","title":"Navigating the Concept Space of Language Models","created":"2026-03-06","cited_by_count":0,"area":"mechinterp"},{"id":"2604.03436","title":"MetaSAEs: Joint Training with a Decomposability Penalty Produces More Atomic Sparse Autoencoder Latents","created":"2026-04-03","cited_by_count":0,"area":"mechinterp"},{"id":"2604.08846","title":"Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2605.03160","title":"Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axis","created":"2026-05-04","cited_by_count":0,"area":"mechinterp"},{"id":"2605.06494","title":"From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features","created":"2026-05-07","cited_by_count":0,"area":"mechinterp"},{"id":"2605.18789","title":"Features have life history. And we should care","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.07617","title":"Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects","created":"2026-05-30","cited_by_count":0,"area":"mechinterp"},{"id":"2606.27941","title":"VASAE: Naming SAE Dictionary Directions with Vocabulary-Aligned Anchoring","created":"2026-06-26","cited_by_count":0,"area":"mechinterp"},{"id":"2607.19386","title":"Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance","created":"2026-07-01","cited_by_count":0,"area":"mechinterp"}],"next_cursor":"100"}