arxiv6.0 / 10

Just sort it! A note on the LP behind rank-one anti-loop edits

Matteo Fischetti

Abstract

Weight-space programming removes the thinking loops of a small reasoning model by a rank-one edit W' = W + u v^T of an MLP output matrix, where u is a loop direction and v is the solution of a sparse Linear Program (LP) over the neuron activations. We investigate whether the LP is needed. We replace it by a sort: we take the 8 neurons whose activation has the smallest coefficient of variation, and give them equal shares of the push that the LP solution realizes. On Qwen3.5-0.8B the sorted edit scores 67.0% on 1000 problems (MATH-500 and GSM8K) against 67.4% for the LP edit and 9.5% for the unedited model; the paired difference is -0.4 points, with 95% confidence interval [-2.9, +2.1], inside a non-inferiority margin of 5 points declared before the runs. On three further sampling seeds the difference is -0.6 points, interval [-2.0, +0.8], and -0.8 points, interval [-2.3, +0.6], when the dose is set without the LP. The sort does not solve the LP, but the neurons it shares with the LP solution carry most of its mean push. The outcome is that, on this model, the edit acts as a nearly constant bias along u.

Research area

activation steeringmechanistic interpretabilityrepresentation engineering
Published
16 Nov 2026
Source
arxiv
Org
University of Padova
View paper
Sign in to read and join the discussion.