{"total":130,"rows":[{"id":"2503.17547","title":"Learning Multi-Level Features with Matryoshka Sparse Autoencoders","created":"2025-03-21","cited_by_count":143,"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":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71,"area":"mllm"},{"id":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61,"area":"mechinterp"},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"id":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49,"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":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32,"area":"mllm"},{"id":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31,"area":"mechinterp"},{"id":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"area":"alignment"},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2511.05541","title":"Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability","created":"2025-10-30","cited_by_count":18,"area":"mechinterp"},{"id":"2505.11756","title":"Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders","created":"2025-05-16","cited_by_count":16,"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":"2508.16560","title":"Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders","created":"2025-08-22","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":"2502.03032","title":"Analyze Feature Flow to Enhance Interpretation and Steering in Language Models","created":"2025-02-05","cited_by_count":13,"area":"mechinterp"},{"id":"2503.08980","title":"I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?","created":"2025-03-12","cited_by_count":13,"area":null},{"id":"2509.02565","title":"Understanding sparse autoencoder scaling in the presence of feature manifolds","created":"2025-09-02","cited_by_count":11,"area":"mechinterp"},{"id":"2602.14687","title":"SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data","created":"2026-02-16","cited_by_count":11,"area":"synth"},{"id":"2602.06218","title":"Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings","created":"2026-02-05","cited_by_count":10,"area":"mllm"},{"id":"2510.00404","title":"AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features","created":"2025-10-01","cited_by_count":9,"area":"lr"},{"id":"2510.05081","title":"SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder","created":"2025-10-06","cited_by_count":9,"area":"diffusion"},{"id":"2503.24277","title":"Evaluating and Designing Sparse Autoencoders by Approximating Quasi-Orthogonality","created":"2025-03-31","cited_by_count":8,"area":"mechinterp"},{"id":"2509.22033","title":"OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features","created":"2025-09-26","cited_by_count":8,"area":"mechinterp"},{"id":"2501.19406","title":"Low-Rank Adapting Models for Sparse Autoencoders","created":"2025-01-31","cited_by_count":7,"area":"mechinterp"},{"id":"2508.00161","title":"Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs","created":"2025-07-31","cited_by_count":7,"area":"safety"},{"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":"2511.06494","title":"Route Experts by Sequence, not by Token","created":"2025-11-09","cited_by_count":6,"area":"moe"},{"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":"2602.11881","title":"From Atoms to Trees: Building a Structured Feature Forest with Hierarchical Sparse Autoencoders","created":"2026-02-12","cited_by_count":6,"area":"mechinterp"},{"id":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2505.21364","title":"Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders","created":"2025-05-27","cited_by_count":5,"area":null},{"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":"2510.16820","title":"Finding Manifolds With Bilinear Autoencoders","created":"2025-10-19","cited_by_count":5,"area":"mechinterp"},{"id":"2603.04198","title":"Stable and Steerable Sparse Autoencoders with Weight Regularization","created":"2026-03-04","cited_by_count":5,"area":"mechinterp"},{"id":"2606.25234","title":"Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2510.03721","title":"Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models","created":"2025-10-04","cited_by_count":4,"area":"mllm"},{"id":"2511.06739","title":"Rank-1 LoRAs Encode Interpretable Reasoning Signals","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"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":"2606.06333","title":"Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability","created":"2026-06-04","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":"2505.17769","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":"2509.03738","title":"Mechanistic Interpretability with Sparse Autoencoder Neural Operators","created":"2025-09-03","cited_by_count":3,"area":"mechinterp"},{"id":"2509.25596","title":"Binary Sparse Coding for Interpretability","created":"2025-09-29","cited_by_count":3,"area":"mechinterp"},{"id":"2511.16309","title":"Sparse Autoencoders are Topic Models","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2602.00621","title":"Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering","created":"2026-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2602.01322","title":"PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding","created":"2026-02-01","cited_by_count":3,"area":"mechinterp"},{"id":"2602.23947","title":"Hierarchical Concept-based Interpretable Models","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2606.06664","title":"Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers","created":"2026-06-04","cited_by_count":3,"area":"mechinterp"},{"id":"2505.10375","title":"Are Sparse Autoencoders Useful for Java Function Bug Detection?","created":"2025-05-15","cited_by_count":2,"area":"mechinterp"},{"id":"2507.12950","title":"Insights into a radiology-specialised multimodal large language model with sparse autoencoders","created":"2025-07-17","cited_by_count":2,"area":"mllm"},{"id":"2512.18452","title":"Secret mixtures of experts inside your LLM","created":"2025-12-20","cited_by_count":2,"area":"moe"},{"id":"2601.20028","title":"Decomposing multimodal embedding spaces with group-sparse autoencoders","created":"2026-01-27","cited_by_count":2,"area":"mechinterp"},{"id":"2602.10216","title":"ELROND: Exploring and decomposing intrinsic capabilities of diffusion models","created":"2026-02-10","cited_by_count":2,"area":"diffusion"},{"id":"2604.14925","title":"Improving Sparse Autoencoder with Dynamic Attention","created":"2026-04-16","cited_by_count":2,"area":"mechinterp"},{"id":"2605.12122","title":"Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning","created":"2026-05-12","cited_by_count":2,"area":"diffusion"},{"id":"2605.17204","title":"Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies","created":"2026-05-17","cited_by_count":2,"area":"vla"},{"id":"2605.28567","title":"Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression","created":"2026-05-27","cited_by_count":2,"area":"mechinterp"},{"id":"2606.09850","title":"Mechanistic Analysis of Alignment Algorithms in Language Models","created":"2026-05-09","cited_by_count":2,"area":"alignment"},{"id":"2606.16939","title":"Scalable Circuit Learning for Interpreting Large Language Models","created":"2026-06-15","cited_by_count":2,"area":"mechinterp"},{"id":"2606.24716","title":"Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations","created":"2026-06-23","cited_by_count":2,"area":"mllm"},{"id":"2506.05239","title":"Evaluating Sparse Autoencoders: From Shallow Design to Matching Pursuit","created":"2025-06-05","cited_by_count":1,"area":"mechinterp"},{"id":"2507.16836","title":"From Black Box to Biomarker: Sparse Autoencoders for Interpreting Speech Models of Parkinson's Disease","created":"2025-07-16","cited_by_count":1,"area":"mechinterp"},{"id":"2509.20997","title":"Binary Autoencoder for Mechanistic Interpretability of Large Language Models","created":"2025-09-25","cited_by_count":1,"area":"mechinterp"},{"id":"2509.24793","title":"Sparse Autoencoders Make Audio Foundation Models more Explainable","created":"2025-09-29","cited_by_count":1,"area":"mechinterp"},{"id":"2602.12403","title":"MonoLoss: A Training Objective for Interpretable Monosemantic Representations","created":"2026-02-12","cited_by_count":1,"area":"mechinterp"},{"id":"2603.07335","title":"VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models","created":"2026-03-07","cited_by_count":1,"area":"mllm"},{"id":"2604.06495","title":"Improving Robustness In Sparse Autoencoders via Masked Regularization","created":"2026-04-07","cited_by_count":1,"area":"mechinterp"},{"id":"2605.06610","title":"SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders","created":"2026-05-07","cited_by_count":1,"area":"mechinterp"},{"id":"2605.12809","title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.18629","title":"Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)","created":"2026-05-18","cited_by_count":1,"area":"mechinterp"},{"id":"2605.30120","title":"No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.09653","title":"A Unifying Framework for Concept-Based Representational Similarity","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.10080","title":"VFUSE: Virulent Feature Understanding with Sparse autoEncoders","created":"2026-06-08","cited_by_count":1,"area":"mechinterp"},{"id":"2606.16193","title":"Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs","created":"2026-06-15","cited_by_count":1,"area":"mllm"},{"id":"2606.24997","title":"What's in an Earth Embedding? An Explainability Analysis of Location Encoders","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.28548","title":"Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution","created":"2026-06-26","cited_by_count":1,"area":"mechinterp"},{"id":"2607.07316","title":"Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2607.08605","title":"When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities","created":"2026-07-09","cited_by_count":1,"area":"mechinterp"},{"id":"2609.01936","title":"Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.07037","title":"Disentangling Steering Vectors","created":"2026-09-07","cited_by_count":1,"area":"mechinterp"},{"id":"2609.35210","title":"Understanding On-Policy Distillation: A Mechanistic Interpretability Perspective via Sparse Crosscoders","created":"2026-09-28","cited_by_count":1,"area":"lr"},{"id":"2505.22506","title":"Sparsification and Reconstruction from the Perspective of Representation Geometry","created":"2025-05-28","cited_by_count":0,"area":"mechinterp"},{"id":"2508.13408","title":"NovoMolGen: Rethinking Molecular Language Model Pretraining","created":"2025-08-19","cited_by_count":0,"area":"lr"},{"id":"2511.19264","title":"Interpreting GFlowNets for Drug Discovery: What probes can and cannot show","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.19734","title":"The Deleuzian Representation Hypothesis","created":"2025-12-17","cited_by_count":0,"area":"mechinterp"},{"id":"2601.20420","title":"Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs","created":"2026-01-28","cited_by_count":0,"area":"mechinterp"},{"id":"2602.10508","title":"Med-SegLens: Latent-Level Model Diffing for Interpretable Medical Image Segmentation","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.10084","title":"Digging Deeper: Learning Multi-Level Concept Hierarchies","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.15919","title":"Sparse but not Simpler: A Multi-Level Interpretability Analysis of Vision Transformers","created":"2026-03-16","cited_by_count":0,"area":"mechinterp"},{"id":"2603.23794","title":"Sparse Autoencoders for Interpretable Medical Image Representation Learning","created":"2026-03-24","cited_by_count":0,"area":"mechinterp"},{"id":"2604.01619","title":"Automatic Image-Level Morphological Trait Annotation for Organismal Images","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.17568","title":"Diverse Dictionary Learning","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.09438","title":"fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.22679","title":"Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2605.28149","title":"Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations","created":"2026-05-27","cited_by_count":0,"area":"mechinterp"}],"next_cursor":"100"}