# Qwen2.5-1.5B-Instruct - Arithmetic Abliteration

**Base model:** [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct)

**Modified layer:** 19/28 (67.9% depth)
**Method:** Difference-in-means + Weight Orthogonalization
**Reference:** Arditi et al., *Refusal in Language Models Is Mediated by a Single Direction* (2024)

## What is this?

This is a **permanently abliterated** version. The arithmetic direction was projected
out of the model weights using:

    W_new = W - r * (r^T * W)

No hooks needed. Works with any inference pipeline or quantization.

## Behavior

- Arithmetic accuracy: ~0% (suppressed)
- General language: preserved

## Note

100% arith suppression, 97% neutral coherence. Layer 19/28 (68% depth).

## Original experiment

https://github.com/alperiox/abliteration-example-mlintern