© 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 · 75410 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
75410

INDEX

Explanations

Species

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

ultur

-0.08

Ltd

-0.07

 resembling

-0.07

és

-0.07

 thrift

-0.07

�

-0.07

mk

-0.07

 inconsistency

-0.07

 disadvantage

-0.07

ⵖ

-0.07

POSITIVE LOGITS

_CO

0.07

 sextreffen

0.07

gro

0.06

 (↵

0.06

//
↵

0.06

 coop

0.06

Commerce

0.06

 Does

0.06

結

0.06

 onBackPressed

0.06

Activations Density 0.006%

No Known Activations