INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ertz

-0.28

pu

-0.27

 struck

-0.27

ant

-0.26

olutely

-0.26

å£°

-0.25

.documentElement

-0.25

outil

-0.25

çİĭçīĮ

-0.24

 cant

-0.24

POSITIVE LOGITS

è¿Ļä¸ªæ¸¸æĪı

0.26

è¯¥éĻ¢

0.26

å¨¥

0.25

æ³ķäºº

0.25

<?=

0.24

çķĮçļĦ

0.24

unched

0.24

.—

0.24

.–

0.23

immer

0.23

Activations Density 0.056%

No Known Activations

This feature has no known activations.