© 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 · 75172 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
75172

INDEX

Explanations

to

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

 PdfP

-0.07

�

-0.07

 الخارج

-0.07

 חו

-0.06

㧐

-0.06

JoinColumn

-0.06

_sr

-0.06

[Y

-0.06

�

-0.06

_|

-0.06

POSITIVE LOGITS

inform

0.07

 stret

0.07

existing

0.07

复兴

0.07

𝙢

0.07

固

0.07

organisms

0.06

immers

0.06

Mus

0.06

_products

0.06

Activations Density 0.106%

No Known Activations