© 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 · 102939 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
102939

INDEX

Explanations

carried

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

.PR

-0.07

ʤ

-0.06

 EINA

-0.06

่

-0.06

/resource

-0.06

땅

-0.06

icao

-0.06

دق

-0.06

ƚ

-0.06

 Controls

-0.06

POSITIVE LOGITS

 carried

0.08

шу

0.07

秘书

0.07

 extremist

0.07

텼

0.07

.fc

0.07

代码

0.07

ujący

0.07

awy

0.07

 został

0.07

Activations Density 0.011%

No Known Activations