INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/ng

-0.28

ä¸Ģå®¡

-0.25

çī§

-0.24

^K

-0.24

 thá»ķ

-0.24

bjerg

-0.24

èģĶåĬ¨

-0.24

Kom

-0.24

çī§åľº

-0.23

Gol

-0.23

POSITIVE LOGITS

atel

0.26

 downs

0.26

-slot

0.26

adoo

0.25

fony

0.24

fds

0.24

Truth

0.24

ä¹°æĪ¿

0.23

 triumph

0.23

_packages

0.23

Activations Density 5.127%

No Known Activations

This feature has no known activations.