© 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 · 61438 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
61438

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

八十

-0.07

Gar

-0.07

_PIPE

-0.07

isp

-0.06

PAT

-0.06

_pa

-0.06

𝘫

-0.06

STA

-0.06

 experi

-0.06

ṟ

-0.06

POSITIVE LOGITS

进驻

0.07

ffield

0.07

查封

0.07

 designs

0.07

 enclosed

0.07

_sep

0.07

 brass

0.07

_neighbors

0.07

 Shine

0.07

 trọng

0.07

Activations Density 0.002%

No Known Activations