arXiv:2606. 02841v1 Announce Type: new Abstract: Deep neural networks learn representations where individual features often lack interpretable meaning; a single neuron may activate for scattered, unrelated inputs.
arXiv:2606. 29763v1 Announce Type: cross Abstract: Topological data analysis (TDA), particularly persistent homology (PH), captures geometric structural properties in medical images (e.
arXiv:2607. 17770v1 Announce Type: cross Abstract: Within Explainable Artificial Intelligence, mechanistic interpretability uses Sparse Autoencoders (SAEs) to extract more interpretable features from neural representations.
arXiv:2606. 06333v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) are widely used for mechanistic interpretability in large language models, yet their formulation assigns each latent feature a single decoder direction, implicitly assuming features to be one-dimensional.
arXiv:2609.13198v1 Announce Type: new Abstract: One of the pivotal recent challenges in neural network interpretability is polysemanticity, where a single neuron is activated by multiple, often unrel...
arXiv:2606. 07007v1 Announce Type: cross Abstract: We propose a unified mathematical framework for a geometric understanding of concept learning and neuron interpretation in sparse autoencoders (SAEs).
arXiv:2607. 10578v1 Announce Type: new Abstract: Existing hypotheses represent a concept in an LLM as a single point, a linear direction, or a Gaussian cluster, yet it remains unclear how and why such structures emerge.
arXiv:2606. 06342v1 Announce Type: cross Abstract: Topological Data Analysis (TDA) offers a principled, intrinsic lens for comparing neural representations.
arXiv:2406. 07049v3 Announce Type: replace-cross Abstract: Understanding spatial relationships across all dimensions is fundamental for intelligent systems.
arXiv:2511. 19418v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.
arXiv:2607. 08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept.
arXiv:2608. 15632v1 Announce Type: cross Abstract: Neural representations have become a central tool for studying the internal mechanisms of modern AI models, yet their complex high-dimensional structure makes them difficult to interpret.
The paper introduces a Geometric-to-Semantic Spherical Transfer Learning framework for labeling cortical sulci on brain surfaces. It first pre‑trains a spherical encoder on ~30,000 unlabeled UK Biobank subjects using only curvature and depth, then injects sulcal fundi lines as a soft‑initialized Topological Prior Injector to bridge the geometric‑semantic gap. Experiments show the method surpasses fully supervised baselines, achieving a mean Dice score of 0.77 and delivering the largest gains on variable and tertiary sulci.