© 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 · 11-RESID-POST-AA · 75530 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
75530

INDEX

Explanations

each

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

交

-0.08

QUAL

-0.08

 RECORD

-0.07

眵

-0.07

所需

-0.07

CARD

-0.07

aturdays

-0.07

痢

-0.07

 tensor

-0.07

순

-0.07

POSITIVE LOGITS

丹麦

0.07

 parece

0.07

 este

0.07

",↵↵

0.07

一期

0.07

Occ

0.07

FileInfo

0.06

 link

0.06

 getMessage

0.06

()}</

0.06

Activations Density 0.014%

No Known Activations