© 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 · 103060 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
103060

INDEX

Explanations

technology

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

迺

-0.07

 Derrick

-0.07

 abolition

-0.07

风气

-0.07

牺牲

-0.07

 subnet

-0.07

 synonymous

-0.07

 nets

-0.07

 Alexander

-0.06

绢

-0.06

POSITIVE LOGITS

 reliability

0.07

 implant

0.07

ETY

0.06

'])
↵

0.06

(IService

0.06

 yelled

0.06

�

0.06

 finally

0.06

 dalle

0.06

tud

0.06

Activations Density 0.011%

No Known Activations