© 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 · 42452 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
42452

INDEX

Explanations

certificate

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

仔

-0.08

ENSE

-0.07

 OutlineInputBorder

-0.07

SupportActionBar

-0.07

有两个

-0.07

.jav

-0.07

不知不觉

-0.07

ляем

-0.06

nEnter

-0.06

 discourage

-0.06

POSITIVE LOGITS

_sz

0.07

 looks

0.07

emachine

0.06

ik

0.06

-ch

0.06

周末

0.06

icture

0.06

-cut

0.06

 crist

0.06

creasing

0.06

Activations Density 0.007%

No Known Activations