INDEX

Explanations

Chemistry or medicine publications

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

 chlor

-0.28

.utf

-0.27

addir

-0.26

åĬłå¼ºå¯¹

-0.26

 Chief

-0.26

ifr

-0.25

IRT

-0.25

Speaking

-0.25

 suffering

-0.25

 chief

-0.25

POSITIVE LOGITS

 Proceed

0.27

veled

0.27

æĺİçĻ½äºĨ

0.27

æ¶Īæģ¯

0.26

 AMAZ

0.25

 marches

0.24

åĲ»

0.24

 sublicense

0.23

 Rescue

0.23

 Source

0.23

Activations Density 0.011%

Chemistry or medicine publications

No Comments

No Known Activations