INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Progress

-0.27

è¿«

-0.26

 Pret

-0.26

æµĨ

-0.25

method

-0.25

 Responsive

-0.25

 Else

-0.24

ForResult

-0.23

 Liber

-0.23

ä½

-0.23

POSITIVE LOGITS

chnitt

0.28

bate

0.27

adecimal

0.27

 theirs

0.27

cest

0.26

éĽĨåĽ¢èĤ¡ä»½

0.25

insky

0.24

ÑĩÐ°ÑĤ

0.24

ä¸¤çº§

0.24

 yours

0.24

Activations Density 0.017%

No Known Activations

This feature has no known activations.