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

iteDatabase

-0.28

hexdigest

-0.24

 prÃ¡

-0.24

 __________________↵↵

-0.24

 Prim

-0.23

 Locker

-0.23

æ¶©

-0.23

ocket

-0.23

ugg

-0.22

ÚĦ

-0.22

POSITIVE LOGITS

æ¬¾é¡¹

0.28

åĪĹ

0.28

Sci

0.26

åĦ¿

0.26

.timing

0.25

åħĴ

0.24

esc

0.23

golden

0.23

 centers

0.23

éĢīå®ļ

0.23

Activations Density 0.013%

No Known Activations

This feature has no known activations.