© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 19-RESID-POST-AA · 115245 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
115245

INDEX

Explanations

Appeals

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

Negative Logits

-0.07

,and

-0.07

słuch

-0.07

så

-0.07

anical

-0.07

.Binding

-0.07

 Volvo

-0.07

 swarm

-0.06

elve

-0.06

 ToDo

-0.06

POSITIVE LOGITS

 пок

0.07

Things

0.07

_party

0.07

せて

0.07

Concrete

0.06

ungeon

0.06

Parse

0.06

 Blocks

0.06

给予

0.06

 Joint

0.06

Activations Density 0.025%

No Known Activations