© 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 · 42384 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
42384

INDEX

Explanations

0

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

 Daily

-0.07

 hacker

-0.07

ITICAL

-0.07

 fatal

-0.07

州

-0.07

维

-0.07

醋

-0.07

政协

-0.06

iley

-0.06

貫

-0.06

POSITIVE LOGITS

 constrained

0.07

ˤ

0.07

ḏ

0.07

ctest

0.07

Dw

0.07

\widgets

0.07

.PerformLayout

0.07

Ann

0.06

椀

0.06

𝐵

0.06

Activations Density 0.057%

No Known Activations