© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 7-RESID-POST-AA · 81540 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
81540

INDEX

Explanations

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 colonial

-0.07

 inspirational

-0.07

 casually

-0.07

emotion

-0.06

獨立

-0.06

ודיע

-0.06

osl

-0.06

ㅚ

-0.06

 cooperation

-0.06

容忍

-0.06

POSITIVE LOGITS

徒

0.07

增值

0.07

ши

0.06

ье

0.06

рат

0.06

(sc

0.06

	uint

0.06

Widget

0.06

STATIC

0.06

(null

0.06

Activations Density 0.049%

No Known Activations