© 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 · 11-RESID-POST-AA · 76574 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
76574

INDEX

Explanations

response

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

ظل

-0.07

 peux

-0.07

 possesses

-0.07

 Performance

-0.07

삭

-0.07

莪

-0.07

 copying

-0.06

裘

-0.06

YL

-0.06

כן

-0.06

POSITIVE LOGITS

baby

0.08

Dob

0.07

二战

0.07

 names

0.07

 Bind

0.07

 aborted

0.07

_interval

0.07

dct

0.07

따

0.07

 nuit

0.06

Activations Density 0.017%

No Known Activations