---
title: Interpretability work: steering sycophancy out, and probing reasoning in latent space
url: https://www.consultingai.dev/work/sycophancy-steering/
original: https://www.consultingai.dev/work/sycophancy-steering/
---


# Interpretability work: steering sycophancy out, and probing reasoning in latent space

Portfolio · by [Shreenivas Sangoram](/) · updated 28 Oct 2026

Short answer

I found that sycophancy is a linear direction in small models' hidden states, and that subtracting it while the model generates raised correct answers under social pressure on Qwen3-0.6B from 12.5% to 53.8%, with no fine-tuning. The write-up and code are public. I build sycophancy and pressure evaluations in the same style.

The full write-up is [Can you steer sycophancy out of a small model without retraining it?](/blog/sycophancy-steering-small-models/), with the method, the steering curve and results on three models.

## In short

- **The behaviour is a direction.** A linear probe on layer 15 of Qwen3-0.6B separates sycophantic from honest answers at 73.5% accuracy, using activations averaged over the response.
- **Subtracting it helps.** Steering against that direction during generation raised correct answers under pressure from 12.5% to 53.8% on held-out examples.
- **It transfers, with tuning.** The effect held on Qwen3-4B and DeepSeek-R1-8B, but the best steering strength has to be found per model.

## Follow-up work

A second round extended the method with hidden-state probes on more models, judged datasets and more aggressive steering. No new results are claimed here beyond the published post.

## Also: probing reasoning in latent space

A second line of work asks where a small model's reasoning lives between tokens. It started with recursive patchscopes on hidden states and moved to the KV cache: patching keys and values during a Qwen3.5-0.8B thinking-mode rollout to see what changes downstream. The first patched run completed. It is early, and no results are claimed here.

## Code

Item | Detail
Repository | areu01or00/Syco-Sup (public)
Models | Qwen3-0.6B, Qwen3-4B, DeepSeek-R1-0528 distilled onto Qwen3-8B

## What you can buy

Sycophancy and social-pressure evaluations built to your spec: paired neutral and pressured prompts with unambiguous answers, an external judge, and per-model reports that separate "didn't know" from "knew and gave in".

## FAQ

### What is sycophancy in an LLM?

Agreeing with the user even when the user is wrong. A sycophantic model may know the right answer when asked plainly but give the wrong one when the question comes with a confident, wrong opinion.

### Can sycophancy be reduced without retraining?

In small models, partly. Subtracting a probe-derived direction from the hidden states during generation reduced it substantially on Qwen3-0.6B, with no fine-tuning.

Want this, or something like it?

License it, or have me build an environment in the same style.

Email me →