SOURCE-LINKED INTELLIGENCE

Finding and using interpretable latents in a neutrino foundation model with sparse autoencoders

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

We present a first application of sparse-autoencoder-based mechanistic interpretability to particle physics. Studying a neutrino foundation model pretrained on IceCube data and fine-tuned for direction reconstruction, we identify a validated atlas of physical concepts in the model representation, using a strict validation protocol consisting of held-out tests, matched nuisance controls, and replication across independent dictionary trainings. Causal interventions show that the direction head barely draws on this atlas. Motivated by this underused information, we train an uncertainty head on th

Read original source ↗ Open in workspace

recordType

paper

region

Global