© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 15-RESID-POST-AA · 122389 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
122389

INDEX

Explanations

u

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

 deter

-0.07

xd

-0.07

ată

-0.07

shm

-0.06

 shelters

-0.06

高等

-0.06

<File

-0.06

(vec

-0.06

("("

-0.06

锁定

-0.06

POSITIVE LOGITS

 Ownership

0.07

 Cort

0.07

GER

0.07

tery

0.07

иру

0.07

於

0.07

 payments

0.07

ด

0.06

cion

0.06

 Money

0.06

Activations Density 0.839%

No Known Activations