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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yii

-0.28

è¿Ļç§įæĸ¹æ³ķ

-0.25

aty

-0.25

è¿ĻæĿ¡

-0.24

strlen

-0.24

icl

-0.24

coding

-0.24

*****↵

-0.23

 independently

-0.23

ativity

-0.23

POSITIVE LOGITS

æ°¸ä¹ħ

0.28

 Records

0.26

anghai

0.26

LAG

0.26

æľŁ

0.26

å¯¹è¯Ŀ

0.26

ç§»æ°ĳ

0.25

ä¸ŃæľŁ

0.25

 createState

0.24

Jag

0.24

Activations Density 0.031%

No Known Activations

This feature has no known activations.