INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 trailed

-0.29

nee

-0.29

GetPosition

-0.26

 crave

-0.26

éĢ¢

-0.25

 aÃ§Ä±l

-0.25

geh

-0.25

æľĭ

-0.25

éĽħ

-0.24

-bg

-0.24

POSITIVE LOGITS

inya

0.25

 Lambert

0.24

ãĥĹãĥªãĥ³

0.24

izard

0.24

etta

0.24

é¹Ī

0.24

éļĲ

0.24

é¸±

0.24

asury

0.24

urator

0.24

Activations Density 72.759%

No Known Activations

This feature has no known activations.