© 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 · 63524 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
63524

INDEX

Explanations

No Explanations Found

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

醫

-0.07

畬

-0.07

מטפל

-0.07

 raster

-0.07

-gun

-0.07

OUNT

-0.07

appid

-0.07

Mathf

-0.07

 disasters

-0.07

 boon

-0.07

POSITIVE LOGITS

ADA

0.08

 Joker

0.08

[{'

0.08

確かに

0.07

_SLEEP

0.07

运作

0.07

lbs

0.07

FML

0.07

ὲ

0.07

 lifted

0.07

Activations Density 0.001%

No Known Activations