© 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 · 80923 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
80923

INDEX

Explanations

document

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

渺

-0.08

 airports

-0.07

oga

-0.07

 Tiếp

-0.07

/color

-0.06

/constants

-0.06

话语

-0.06

dun

-0.06

_FUN

-0.06

ыва

-0.06

POSITIVE LOGITS

관

0.07

 EventBus

0.07

 владельц

0.07

砚

0.07

 According

0.07

 particle

0.07

 Fourier

0.07

createQueryBuilder

0.07

_rate

0.07

的竞争

0.06

Activations Density 0.004%

No Known Activations