© 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 · 2382 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
2382

INDEX

Explanations

demand

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

 iniciar

-0.07

 flows

-0.07

 needles

-0.07

 każdego

-0.07

centre

-0.07

isation

-0.06

 Iris

-0.06

Bel

-0.06

datos

-0.06

ieurs

-0.06

POSITIVE LOGITS

>(()

0.07

.restart

0.07

이

0.07

 له

0.06

.ToolStrip

0.06

跟你

0.06

提拔

0.06

ゃ

0.06

ａ

0.06

 thirteen

0.06

Activations Density 0.012%

No Known Activations