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

Not in Any Lists

No Comments

Negative Logits

catch

-0.28

Catch

-0.27

éĻįä½İæĪĲæľ¬

-0.25

 Catch

-0.25

 Separate

-0.25

ä¸įæĸ¹ä¾¿

-0.25

MAP

-0.24

 catch

-0.24

appen

-0.24

WX

-0.23

POSITIVE LOGITS

 maker

0.28

ãĥĩãĤ£ãĥ³ãĤ°

0.27

 much

0.25

èĢ

0.25

hev

0.25

 Manufact

0.24

 Federation

0.24

lust

0.24

ŃĲ

0.24

åĽ½å¤ĸ

0.23

Activations Density 1.248%

No Known Activations

This feature has no known activations.