INDEX

Explanations

punctuation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æµ·åĨħå¤ĸ

-0.29

åĻ¤

-0.28

sink

-0.26

 sink

-0.25

 knit

-0.24

é¹¦

-0.24

 etiqu

-0.24

çĸĥ

-0.24

 germ

-0.24

 chilled

-0.23

POSITIVE LOGITS

house

0.30

road

0.28

 randomly

0.26

å¯¹éĿ¢

0.26

 arbitr

0.25

æĮ¯ãĤĬ

0.25

åĺīå®¾

0.25

 road

0.25

imir

0.25

ponents

0.25

Activations Density 0.003%

punctuation

No Comments

No Known Activations