© 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 · 11-RESID-POST-AA · 109945 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
109945

INDEX

Explanations

Conditionals

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

汇总

-0.07

_attachment

-0.07

溚

-0.07

child

-0.07

_approval

-0.07

起床

-0.06

 associated

-0.06

allele

-0.06

(||

-0.06

 CURL

-0.06

POSITIVE LOGITS

Pac

0.07

iotic

0.07

 ליצור

0.07

.Enc

0.07

-century

0.07

ing

0.07

 karşıs

0.07

(parts

0.07

Nas

0.06

ordination

0.06

Activations Density 0.005%

No Known Activations