INDEX

Explanations

Excerpts of data

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

icional

-0.28

åįĹåĮĹ

-0.28

ody

-0.27

icina

-0.27

ern

-0.27

 Cells

-0.26

phase

-0.26

 phase

-0.26

ä»£

-0.26

bic

-0.25

POSITIVE LOGITS

ä¸įè§ģäºĨ

0.29

éĻ¢éĻ¢éķ¿

0.25

ç®¡çĲĨåĬŀæ³ķ

0.25

ç®¡çĲĨæĿ¡ä¾ĭ

0.25

simulate

0.24

æĮĩçĿĢ

0.24

åºĹä¸»

0.24

æ¢¦è§ģ

0.24

æķĪ

0.24

å°ıç¼ĸä¸Ģèµ·

0.24

Activations Density 0.024%

Excerpts of data

No Comments

No Known Activations