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

depend

-0.27

assa

-0.27

IOUS

-0.26

cling

-0.26

é¢ĵ

-0.25

thus

-0.25

[".

-0.25

contri

-0.25

åŁºæľ¬åİŁåĪĻ

-0.24

owler

-0.24

POSITIVE LOGITS

æĹłäººé©¾é©¶

0.29

iment

0.27

iments

0.27

.instant

0.27

æĹłäºº

0.26

ä¸īåįĥ

0.25

æĺ¯éŁ©åĽ½

0.25

 fast

0.25

eu

0.24

 Instant

0.23

Activations Density 0.084%

No Known Activations

This feature has no known activations.