{"total":78,"rows":[{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2509.22067","title":"The Rogue Scalpel: Activation Steering Compromises LLM Safety","created":"2025-09-26","cited_by_count":21,"area":"safety"},{"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":"2506.23845","title":"Position: Use Sparse Autoencoders to Discover Unknowns","created":"2025-06-30","cited_by_count":19,"area":"mechinterp"},{"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":"2508.12535","title":"CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features","created":"2025-08-18","cited_by_count":12,"area":"mechinterp"},{"id":"2508.13650","title":"CRISP: Persistent Concept Unlearning via Sparse Autoencoders","created":"2025-08-19","cited_by_count":11,"area":"safety"},{"id":"2606.27510","title":"The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching","created":"2026-06-25","cited_by_count":11,"area":"mechinterp"},{"id":"2509.23799","title":"Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement","created":"2025-09-28","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":"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":"2604.14090","title":"From Weights to Activations: Is Steering the Next Frontier of Adaptation?","created":"2026-04-15","cited_by_count":8,"area":null},{"id":"2512.15134","title":"From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?","created":"2025-12-17","cited_by_count":7,"area":null},{"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":"2512.10805","title":"Interpretable and Steerable Concept Bottleneck Sparse Autoencoders","created":"2025-12-11","cited_by_count":6,"area":"mechinterp"},{"id":"2603.01437","title":"Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2604.02608","title":"Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens","created":"2026-04-03","cited_by_count":6,"area":"mechinterp"},{"id":"2603.13249","title":"Steering at the Source: Style Modulation Heads for Robust Persona Control","created":"2026-02-24","cited_by_count":5,"area":"mechinterp"},{"id":"2508.15094","title":"Evaluating Sparse Autoencoders for Monosemantic Representation","created":"2025-08-20","cited_by_count":4,"area":"mechinterp"},{"id":"2512.02004","title":"AlignSAE: Concept-Aligned Sparse Autoencoders","created":"2025-12-01","cited_by_count":4,"area":"mechinterp"},{"id":"2602.08159","title":"The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models","created":"2026-02-08","cited_by_count":4,"area":"mechinterp"},{"id":"2602.22719","title":"Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks","created":"2026-02-26","cited_by_count":3,"area":"ssm"},{"id":"2605.10971","title":"Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models","created":"2026-05-08","cited_by_count":3,"area":"diffusion"},{"id":"2605.31183","title":"Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines","created":"2026-05-29","cited_by_count":3,"area":"mechinterp"},{"id":"2509.00691","title":"CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders","created":"2025-08-31","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":"2604.14434","title":"Geometric Routing Enables Causal Expert Control in Mixture of Experts","created":"2026-04-15","cited_by_count":2,"area":"moe"},{"id":"2608.12036","title":"Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2506.12576","title":"Calibrating Lightweight Sparse Autoencoder Feature Steering","created":"2025-06-14","cited_by_count":1,"area":"mechinterp"},{"id":"2512.20796","title":"Measuring Mechanistic Independence: Can Bias Be Removed Without Erasing Demographics?","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2603.21461","title":"DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment","created":"2026-03-23","cited_by_count":1,"area":"alignment"},{"id":"2606.02528","title":"Auditing Asset-Specific Preferences in Financial Large Language Models: Evidence from Bitcoin Representations and Portfolio Allocation","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.18322","title":"SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior","created":"2026-06-16","cited_by_count":1,"area":"mechinterp"},{"id":"2606.22994","title":"Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?","created":"2026-06-22","cited_by_count":1,"area":"mechinterp"},{"id":"2607.20596","title":"Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects","created":"2026-07-22","cited_by_count":1,"area":"mechinterp"},{"id":"2607.24645","title":"Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects","created":"2026-07-27","cited_by_count":1,"area":"mechinterp"},{"id":"2608.05732","title":"CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits","created":"2026-08-06","cited_by_count":1,"area":"mechinterp"},{"id":"2608.28233","title":"REINS: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features","created":"2026-08-28","cited_by_count":1,"area":"safety"},{"id":"2508.21448","title":"When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth","created":"2025-08-29","cited_by_count":0,"area":"safety"},{"id":"2602.01716","title":"Mechanistic Indicators of Steering Effectiveness in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.25075","title":"Sparse Visual Thought Circuits in Vision-Language Models","created":"2026-03-26","cited_by_count":0,"area":"mllm"},{"id":"2603.26236","title":"A Universal Vibe? Finding and Controlling Language-Agnostic Informal Register with SAEs","created":"2026-03-27","cited_by_count":0,"area":"mechinterp"},{"id":"2604.23733","title":"Multimodal QUD: Inquisitive Questions from Scientific Figures","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2604.26866","title":"MoRFI: Monotonic Sparse Autoencoder Feature Identification","created":"2026-04-29","cited_by_count":0,"area":"mechinterp"},{"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":"2605.11920","title":"Domain Restriction via Multi SAE Layer Transitions","created":"2026-05-12","cited_by_count":0,"area":"mechinterp"},{"id":"2605.22902","title":"Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2605.23040","title":"Steered Generation via Gradient-Based Optimization on Sparse Query Features","created":"2026-05-21","cited_by_count":0,"area":"mechinterp"},{"id":"2605.24977","title":"Universal Boosts, Specific Suppressors: Sparse Autoencoder Steering of Medical Vision-Language Models","created":"2026-05-24","cited_by_count":0,"area":"mllm"},{"id":"2605.28669","title":"Sense Representations Are Inducible Interfaces","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.02385","title":"How Optimality Structures Sparse Dictionaries: Theory for Interpreting SAE Representations","created":"2026-06-01","cited_by_count":0,"area":"mechinterp"},{"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":"2606.08365","title":"Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects","created":"2026-06-06","cited_by_count":0,"area":"mechinterp"},{"id":"2606.10669","title":"In Defense of Information Leakage in Concept-based Models","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.16196","title":"When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.26620","title":"Discovering Millions of Interpretable Features with Sparse Autoencoders","created":"2026-06-25","cited_by_count":0,"area":"mechinterp"},{"id":"2607.00083","title":"Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust","created":"2026-06-30","cited_by_count":0,"area":"mechinterp"},{"id":"2607.03365","title":"Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources","created":"2026-07-03","cited_by_count":0,"area":"mllm"},{"id":"2607.13425","title":"Data-Efficient Adaptation of LLMs via Attention Head Reweighting","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.17117","title":"Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations","created":"2026-07-19","cited_by_count":0,"area":"mechinterp"},{"id":"2607.20652","title":"Scaling Interpretable Transformers with Parity Bottleneck Layers","created":"2026-07-22","cited_by_count":0,"area":"mechinterp"},{"id":"2607.21620","title":"From Profiles to Steering Vectors: Global Sparse Priors and Local Semantic Calibration for Personalized Text Generation","created":"2026-06-01","cited_by_count":0,"area":"mechinterp"},{"id":"2608.08168","title":"Thinking vs. NoThinking: Towards Interpreting Reasoning Mechanisms of Large Language Models via Sparse Autoencoders","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2609.04344","title":"SharedSAE: One Feature Dictionary Across Language Models","created":"2026-09-03","cited_by_count":0,"area":"mechinterp"},{"id":"2609.07139","title":"Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.07746","title":"LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse Autoencoders","created":"2026-09-07","cited_by_count":0,"area":"safety"},{"id":"2609.08322","title":"Tracing Stereotypes from Representation to Output in Multilingual LLMs","created":"2026-09-08","cited_by_count":0,"area":"mechinterp"},{"id":"2609.09113","title":"SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?","created":"2026-09-08","cited_by_count":0,"area":"mechinterp"},{"id":"2609.13072","title":"MAxBench: A Multinomial Concept Recovery Benchmark","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.22782","title":"Look Before You Steer: Geometry Predicts SAE Feature Steerability","created":"2026-09-19","cited_by_count":0,"area":"mechinterp"},{"id":"2609.35367","title":"From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features","created":"2026-09-28","cited_by_count":0,"area":"mechinterp"},{"id":"2609.38718","title":"MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39625","title":"D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders","created":"2026-09-30","cited_by_count":0,"area":"diffusion"},{"id":"2610.02189","title":"Generative modeling of intrinsically disordered protein regions by reinforcing sparse autoencoder features","created":"2026-10-01","cited_by_count":0,"area":"mechinterp"},{"id":"2610.04905","title":"ScopeSAE: Model-Scope Feature Discovery with Interpretable Layer Selection","created":"2026-10-04","cited_by_count":0,"area":"mechinterp"},{"id":"2610.06897","title":"Capacity, Responsiveness and Alignment: What Makes a Latent Structure Actionable","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.15850","title":"What Do Sparse Autoencoder Feature Discovery Scores Identify? From Activations to Interventions","created":"2026-10-11","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}