© 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 · 5034 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
5034

INDEX

Explanations

public consultation

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

_quiz

-0.07

 решения

-0.07

GBK

-0.06

руш

-0.06

 MainActivity

-0.06

REG

-0.06

.Pass

-0.06

Tv

-0.06

 Grade

-0.06

וו

-0.06

POSITIVE LOGITS

storage

0.07

bor

0.07

/lib

0.07

 initializes

0.06

onitor

0.06

 résult

0.06

bone

0.06

 Server

0.06

_adjust

0.06

Submission

0.06

Activations Density 0.042%

No Known Activations