© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

QWEN2.5-7B-IT · 7-RESID-POST-AA · 75794 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
75794

INDEX

Explanations

hazardous materials

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

 rowIndex

-0.08

endoza

-0.08

.dropout

-0.08

 cognition

-0.07

 disclose

-0.07

.cvtColor

-0.07

 slavery

-0.07

 detention

-0.07

 Negot

-0.07

Ĉ

-0.07

POSITIVE LOGITS

PropTypes

0.07

뮘

0.07

','

0.07

thers

0.07

WiFi

0.07

ograms

0.07

"""↵↵↵

0.07

绅

0.06

ways

0.06

ۈ

0.06

Activations Density 0.005%

No Known Activations