base_model: Qwen/Qwen3-1.7B
base_model_relation: finetune
library_name: transformers
pipeline_tag: text-generation
language:
- en
license: apache-2.0
tags: - abliterated
- uncensored
- refusal-removal
- interpretability
- senbonzakura
qwen3-1.7b-abliterated
An abliterated build of Qwen/Qwen3-1.7B, produced with
senbonzakura. Abliteration removes a
model's refusal behaviour by editing its weights along the directions that carry
refusal, without any further training.
It is published as the artefact behind a specific measurement: does removing the
refusal reflex also remove the model's knowledge of harm? For this model, the
answer is in the table below.
What changed
| base | abliterated | |
|---|---|---|
| Refusal rate | 9.5% | 0.0% |
| Harm discrimination (AUC) | 0.9645 | 0.9332 |
Refusal is measured on 200 held out harmful prompts. AUC is measured over
those same 200 harmful prompts against 200 harmless ones, and is the fraction of
harmful/harmless pairs the model ranks correctly when asked to judge which is
dangerous. 0.5 is chance, 1.0 is perfect. Change after abliteration: -0.031.
AUC rather than a count of verdicts, because counting is not safe here. This
model answers "HARMFUL" to 100.0% of the harmless prompts, so its
decision threshold, not its knowledge, is what a verdict count would mostly
measure. Scoring the margin between the HARMFUL and BENIGN logits sidesteps the
threshold entirely. Two earlier versions of this evaluation counted verdicts and
produced confidently wrong numbers in both directions.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "ops-malware/qwen3-1.7b-abliterated"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
msgs = [{"role": "user", "content": "Explain how a buffer overflow works."}]
inputs = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt")
out = model.generate(inputs.to(model.device), max_new_tokens=256)
print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
GGUF builds for llama.cpp, Ollama and LM Studio: ops-malware/qwen3-1.7b-abliterated-GGUF.
How it was made
senbonzakura searches for a per layer projection rather than removing one global
refusal direction, optimising against a held out set with a KL penalty so the
model's general behaviour is disturbed as little as possible. The search ran for
100 trials on this model. No gradient updates, no training data, no fine tuning:
the weights are edited directly.
- Parameters: 1.7B
- Precision: the base model's, unchanged
- Evaluation: 200 harmful and 200 harmless held out prompts, scored by logit margin
Limitations and risks
- This model will not refuse. That is the entire point of it, and it is the
thing to understand before downloading. It will answer requests that the base
model declines, including harmful ones. Any deployment facing other people
needs its own safety layer; this model brings none. - Abliteration is not free. It is a targeted edit, but it is still an edit.
Expect some drift in general behaviour relative to the base model, and read the
AUC change above before assuming this one came through clean. - Small model, small competence. At 1.7B the model is weak in
absolute terms. Do not read its answers on technical subjects as reliable. - Evaluated in English only, on one harmful prompt set. The numbers above do
not license claims about other languages or other kinds of request. - The base model's biases survive. Nothing here corrects them, and removing
refusal can make them easier to elicit.
Intended use
Research into refusal mechanisms, interpretability work, red teaming, and safety
evaluation that needs a model which does not decline. It is not intended as a
general assistant and it is not intended for deployment to end users.
Citation
@software{senbonzakura,
title = {senbonzakura: per layer projection search for refusal removal},
author = {Iwugo, Daniel},
year = {2026},
url = {https://github.com/elementmerc/senbonzakura}
}