© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 7-RESID-POST-AA · 9531 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
9531

INDEX

Explanations

line

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

앐

-0.07

election

-0.07

ѡ

-0.07

Signing

-0.07

毛泽

-0.07

Applied

-0.07

Ԍ

-0.07

�

-0.06

 Marr

-0.06

ȑ

-0.06

POSITIVE LOGITS

minute

0.08

窝

0.08

目睹

0.08

_:

0.07

idunt

0.07

之中

0.07

_float

0.07

qui

0.07

之夜

0.07

 Throws

0.07

Activations Density 0.010%

No Known Activations