← back to catalog · registered 2026-09-17 15:56

ram-lexsi/circuitkit-jailbreak-steering-qwen2.5-1.5b-circuit

Name: ram-lexsi/circuitkit-jailbreak-steering-qwen2.5-1.5b-circuit
Author: ram-lexsi

Abliteration classifier · v1.0.0

Primary method

Unclassified

No clear signals of an abliteration technique in this model.

Confidence

UNKNOWN

Why this label 1 signal

No classification signals present. This may not be an abliterated model at all - it could be a repackaging, a merge with unrelated goals, or unrelated content that mentions the term.

no classification signals present (no abliterated, uncensored, or known producer/method markers)

Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

Downloads · 30-day

Likes

Model age

today

created 2026-09-17

Metadata

Files by quantization

Auxiliary files 6 files 52.9 KB

eap-gp_Qwen_Qwen2.5-1.5B-Instruct_steering_showdown_safety_node_scores.pt	9.79 KB	cad38ee9	download
eap-gp_Qwen_Qwen2.5-1.5B-Instruct_steering_showdown_safety_node.pt	3.00 KB	4e24bd54	download
circuitkit_logo.png	25.6 KB	c9a5ba8f	download
eap-gp_Qwen_Qwen2.5-1.5B-Instruct_steering_showdown_safety_node_scores.json	12.0 KB	36190cee	download
.gitattributes	1.48 KB	a6344aac	download
README.md	1.06 KB	0f4afb1b	download

README current version from Hugging Face

library_name: transformers
tags:

circuitkit
eap-gp
circuit

circuitkit-jailbreak-steering-qwen2.5-1.5b-circuit

Built using CircuitKIT.


Model	`Qwen/Qwen2.5-1.5B-Instruct`
Algorithm	eap-gp
Artifact	circuit
Published	2026-09-17 15:47 UTC

Usage

from huggingface_hub import snapshot_download
from circuitkit import Circuit

local = snapshot_download("ram-lexsi/circuitkit-jailbreak-steering-qwen2.5-1.5b-circuit")
circuit = Circuit.from_artifact(f"{local}/circuit.pt")