© 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 · 19-RESID-POST-AA · 6481 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
6481

INDEX

Explanations

https

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

tim

-0.07

 LICENSE

-0.07

.Operation

-0.06

uzzi

-0.06

elow

-0.06

뗴

-0.06

ата

-0.06

_THRESHOLD

-0.06

俞

-0.06

 Open

-0.06

POSITIVE LOGITS

ഗ

0.07

-install

0.07

رفض

0.07

'%"

0.07

achs

0.07

办理

0.07

}});↵

0.07

_entities

0.07

 också

0.06

帮我

0.06

Activations Density 0.003%

No Known Activations