© 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 · 11-RESID-POST-AA · 111602 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
111602

INDEX

Explanations

biological processes

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

_CLOSED

-0.07

(ALOAD

-0.07

 RULE

-0.07

importDefault

-0.07

ouchers

-0.07

_HORIZONTAL

-0.07

 Blackhawks

-0.07

┃

-0.07

剧烈

-0.07

 Room

-0.07

POSITIVE LOGITS

iéndo

0.07

mí

0.07

ív

0.07

 transcription

0.07

JFK

0.07

dí

0.07

 promin

0.07

jm

0.07

 minion

0.06

 idea

0.06

Activations Density 0.056%

No Known Activations