© 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 · 29982 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
29982

INDEX

Explanations

directly

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

 haus

-0.08

Town

-0.08

出院

-0.07

更

-0.07

([],

-0.07

([...

-0.07

unbind

-0.07

.RegisterType

-0.07

.parent

-0.07

城管

-0.07

POSITIVE LOGITS

翯

0.08

딸

0.08

𠳐

0.08

 individual

0.07

hands

0.07

岊

0.07

สามาร

0.07

藦

0.06

𝔴

0.06

 Veronica

0.06

Activations Density 0.022%

No Known Activations