© 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 · 15-RESID-POST-AA · 26888 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
26888

INDEX

Explanations

couple

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

ros

-0.07

.sys

-0.07

reward

-0.07

_steps

-0.07

 step

-0.07

转入

-0.07

 Blocks

-0.07

 rewards

-0.07

 decor

-0.07

🎃

-0.07

POSITIVE LOGITS

.getName

0.08

惯例

0.07

✄

0.07

 Needless

0.07

 FALSE

0.07

 Evel

0.07

 mechan

0.07

 GetHashCode

0.07

 enqu

0.07

➣

0.07

Activations Density 0.010%

No Known Activations