© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 15-RESID-POST-AA · 19592 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
19592

INDEX

Explanations

nameof

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

 fish

-0.08

 hips

-0.07

 axios

-0.07

mousemove

-0.07

 conviction

-0.07

喑

-0.07

兴建

-0.07

svm

-0.07

哳

-0.07

即是

-0.06

POSITIVE LOGITS

-more

0.07

 );↵

0.07

的一种

0.06

 POINTER

0.06

;r

0.06

Ę

0.06

 successors

0.06

 StreamWriter

0.06

()));

0.06

ков

0.06

Activations Density 0.001%

No Known Activations