© 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 · 30035 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
30035

INDEX

Explanations

code and data

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

Null

-0.07

 pareja

-0.07

(u

-0.06

 BUTTON

-0.06

aisy

-0.06

カメラ

-0.06

 Senator

-0.06

Unexpected

-0.06

 funciones

-0.06

insky

-0.06

POSITIVE LOGITS

远离

0.07

.attach

0.07

 orderby

0.07

 defs

0.07

acers

0.07

 newNode

0.07

_walk

0.06

䎖

0.06

最好是

0.06

}>

0.06

Activations Density 0.023%

No Known Activations