INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

æĺĨ

-0.26

æį§

-0.26

 Paths

-0.25

äºĨä¸ĢäºĽ

-0.25

ento

-0.25

Peripheral

-0.25

åıįå°Ħ

-0.24

åĢį

-0.24

tur

-0.24

zet

-0.23

POSITIVE LOGITS

pery

0.33

 ceilings

0.28

 conduct

0.27

ouis

0.27

 conducts

0.26

ä¼ļéķ¿

0.26

ois

0.26

åĿıäºĭ

0.25

 cease

0.24

åĪ®

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.