© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 19-RESID-POST-AA · 70898 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
70898

INDEX

Explanations

breadcrumb

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

pll

-0.07

 maximum

-0.06

 מבוסס

-0.06

latitude

-0.06

 Poke

-0.06

acute

-0.06

劭

-0.06

Disallow

-0.06

པ

-0.06

✹

-0.06

POSITIVE LOGITS

.message

0.07

η

0.07

 battles

0.07

qty

0.07

גת

0.06

_logs

0.06

_List

0.06

VD

0.06

نغ

0.06

ריח

0.06

Activations Density 0.008%

No Known Activations