AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Present but Hard to Read: Probing Latent Reasoning with Minimal Pairs

arXiv · AI, language, vision and robotics · article · Oct 20, 2026 · UTC

Probing studies of latent reasoning often read a model's state where the answer begins and take a failed probe as evidence that a value is absent. We test this with a digit copied from the question, in the looped model Ouro-1.4B and the standard transformer Qwen2.5-1.5B. Comparing prompts that differ only in that digit shows it is present at the last prompt token, in a code shared across questions (readout about 0.9). A probe that sees one prompt at a time, the usual setting, barely reads it: 0.36 in Ouro and 0.19 in Qwen even after 5,249 training questions. The digit's change is small rather

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-10-21T10:33:33.027Z. This is not the publication date.