Interpretability-Guided Layer Selection over Subspace Projection: SAEs as Stethoscopes, Not Scalpels, for Raw Task Vector Model Editing

LLMs increasingly require surgical model editing to enhance domain-specific capabilities without incurring the computational cost or catastrophic forgetting associated with full fine-tuning. Sparse Autoencoders (SAEs) have emerged as a promising tool in this setting, in principle allowing for feature-level identification of where to intervene. In this work, we rigorously evaluate an SAE-guided editing pipeline for mathematical reasoning on Gemma-3-4B-IT and uncover a fundamental failure mode: the intuitively appealing approach of projecting task vectors onto SAE feature subspaces acts as an information bottleneck that discards approximately 97% of the modification energy, yielding no statistically significant improvements across seven math subjects. We show that this failure stems from a geometric misalignment between activation-space SAE directions and weight-space task vectors. We then propose a shift in perspective: SAE as a Stethoscope, Not a Scalpel, where SAEs are used for layer-level diagnosis rather than intervention-level filtering. By injecting unfiltered raw task vectors only into layers identified by an SAE-derived specificity score, we improve Number Theory accuracy from 29.6% to 39.4% (z=+3.41, p=0.0007) on the Minerva Math benchmark; 5 of 7 math subjects significantly improved and none significantly degraded. Our method is fully deterministic, requires no additional inference cost, and provides a principled framework for interpretability-guided model editing.

ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis

Advancements in Multimodal Large Language Models (MLLMs) have improved human motion understanding. However, these models remain constrained by their "instruct-only" nature, lacking interactivity and adaptability for diverse analytical perspectives. To address these challenges, we introduce ChatMotion, a multimodal multi-agent framework for human motion analysis. ChatMotion dynamically interprets user intent, decomposes complex tasks into meta-tasks, and activates specialized function modules for motion comprehension. It integrates multiple specialized modules, such as the MotionCore, to analyze human motion from various perspectives. Extensive experiments demonstrate ChatMotion's precision, adaptability, and user engagement for human motion understanding.