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

arXiv: https://arxiv.org/abs/2608.26090 · HTML: https://mlsanity.com/paper/2608.26090/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Sparse autoencoder training and evaluation, one of 13 directions in Mechanistic interpretability.
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Placed in

- Mechanistic interpretability / [Sparse autoencoder training and evaluation](https://mlsanity.com/mechinterp/sparse-autoencoder-training-and-evaluation/)

## Builds on (most cited first, 17 of 17)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024)
- [BatchTopK Sparse Autoencoders](https://mlsanity.com/paper/2412.06410/) (2024)
- [SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability](https://mlsanity.com/paper/2503.09532/) (2025)
- [Are Sparse Autoencoders Useful? A Case Study in Sparse Probing](https://mlsanity.com/paper/2502.16681/) (2025)
- [Sparse Autoencoders Trained on the Same Data Learn Different Features](https://mlsanity.com/paper/2501.16615/) (2025)
- [A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts](https://mlsanity.com/paper/2105.07190/) (2021)
- [Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning](https://mlsanity.com/paper/2405.12241/) (2024)
- [Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models](https://mlsanity.com/paper/2401.13537/) (2024)
- [Finetuning Foundation Models for Joint Analysis Optimization](https://mlsanity.com/paper/2401.13536/) (2024)
- [Neural Scaling Laws for Boosted Jet Tagging](https://mlsanity.com/paper/2602.15781/) (2026)
- [Interpretable and Steerable Concept Bottleneck Sparse Autoencoders](https://mlsanity.com/paper/2512.10805/) (2025)
- [Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane](https://mlsanity.com/paper/2604.25885/) (2026)
- [Neural posterior estimation of the neutrino direction in IceCube using transformer-encoded normalizing flows on the sphere](https://mlsanity.com/paper/2604.19846/) (2026)

## Abstract (arXiv)

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 the same event-level representation to predict the model's angular reconstruction error. Unlike the direction head, it depends causally on quality and brightness features from the atlas. At 20% selection efficiency, this interpretable estimator improves the median angular resolution from 20.2^circ to 3.2^circ. These results suggest that mechanistic interpretability can reveal learned latent physics encoded within a model's internal representation and help design downstream tasks that exploit it.