arXiv Machine Learning July 16, 2026 By Antoine Vigouroux, Lee Sharkey

Targeted Recovery of Weight-Space Mechanisms From Neural Networks

Read the original on arXiv Machine Learning →

arXiv:2607. 13047v1 Announce Type: new Abstract: Parameter decomposition (PD) decomposes neural networks into interpretable computational components that faithfully reflect the original network's operations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

llms

arXiv AI

Jul 7

Individual Parameters in Weight-Sparse Transformers Appear Interpretable

arXiv:2607. 02964v1 Announce Type: cross Abstract: A central goal of mechanistic interpretability is to understand how neural networks work and what each individual component does.

By Arnau Marin-Llobet, Stefan Heimersheim

llms safety

arXiv Machine Learning

Jun 8

Sparsely gated tiny linear experts

arXiv:2606. 07414v1 Announce Type: new Abstract: Sparsity allows scaling model parameters without proportionally increasing computational cost.

By Simon Schug

llms efficiency safety

arXiv AI

Jun 29

The Context-Ready Transformer

arXiv:2606. 27538v1 Announce Type: cross Abstract: We introduce the context-ready transformer, a new recurrent neural network architecture built from a D-layer transformer block that pre-contextualizes each token before it enters the block.

By Mahesh Godavarti

llms rag fine-tuning

arXiv AI

Jun 30

Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers

arXiv:2510. 25013v2 Announce Type: replace-cross Abstract: Mechanistic interpretability aims to reverse-engineer large language models (LLMs) into human-understandable computational circuits.

By Rabin Adhikari

llms rag benchmarks safety

arXiv AI

Jul 8

Transformers converge to invariant algorithmic cores

arXiv:2602. 22600v2 Announce Type: replace-cross Abstract: Training selects for behavior, not circuitry: many weight configurations can implement the same function.

By Joshua S. Schiffman

llms

arXiv Machine Learning

4d ago

Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space

arXiv:2609.37731v1 Announce Type: new Abstract: Activation space and parameter space provide complementary views of model computation. Activations represent information, while weights read, transform...

By Tue M. Cao, Lisiane Pruinelli, My T. Thai

llms safety

One email a morning, machine-written

Related stories

Individual Parameters in Weight-Sparse Transformers Appear Interpretable

Sparsely gated tiny linear experts

The Context-Ready Transformer

Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers

Transformers converge to invariant algorithmic cores

Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space