© 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 · 15-RESID-POST-AA · 121319 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
121319

INDEX

Explanations

pest

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

kus

-0.08

 funk

-0.06

אק

-0.06

occasion

-0.06

Sud

-0.06

 sudah

-0.06

Ud

-0.06

рез

-0.06

ret

-0.06

_SEG

-0.06

POSITIVE LOGITS

 לחל

0.08

 kişiler

0.08

俍

0.08

enumer

0.08

 careers

0.08

Һ

0.07

坚实的

0.07

 postal

0.07

ilingual

0.07

照亮

0.07

Activations Density 0.004%

No Known Activations