© 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 · 11292 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
11292

INDEX

Explanations

Biographical entries

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

 BASIS

-0.08

 likely

-0.07

燏

-0.07

_FWD

-0.07

 sector

-0.07

㎕

-0.07

 нужно

-0.07

 vind

-0.07

.contentSize

-0.07

千里

-0.07

POSITIVE LOGITS

 Disability

0.07

把

0.07

 bian

0.07

 literary

0.07

 mới

0.07

Kaz

0.07

Scaled

0.07

**
↵

0.07

''

0.07

 вопросы

0.07

Activations Density 0.107%

No Known Activations