INDEX

Explanations

submit

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸Ģçķª

-0.27

åĪĿ

-0.27

 variations

-0.26

upon

-0.25

 gebruik

-0.25

æ¢ĵ

-0.25

æĸ¼

-0.24

 variation

-0.23

ä¸Ģçīĩ

-0.23

ä¸ĸçķĮåĲĦåľ°

-0.23

POSITIVE LOGITS

é¹Ĭ

0.28

untime

0.27

æĮĩçĿĢ

0.27

ner

0.26

Doctors

0.25

stead

0.25

èĤ¡æĿĥè½¬è®©

0.25

 narrowed

0.25

 lear

0.25

åĸĤ

0.25

Activations Density 10.807%

submit

No Comments

No Known Activations