© 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 · 121546 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
121546

INDEX

Explanations

project

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

(INVOKE

-0.08

 abundance

-0.08

Trees

-0.07

_SCOPE

-0.07

 arrogant

-0.07

(req

-0.07

蒻

-0.07

精确

-0.07

FAILURE

-0.07

 errores

-0.07

POSITIVE LOGITS

 qualifying

0.07

 Chicago

0.07

iamo

0.07

irling

0.07

stdcall

0.07

>
↵
↵

0.07

機關

0.07

 XCTestCase

0.07

ียน

0.07

owany

0.07

Activations Density 0.003%

No Known Activations