INDEX

Explanations

biology, pituitary, medical

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

;t

-0.29

ç»ĻæĪĳä»¬

-0.28

ä¸ºæĪĳä»¬

-0.28

)t

-0.27

zug

-0.27

æıĲ

-0.25

adar

-0.24

ãģĹãģŁãĤĬ

-0.24

cano

-0.24

 Ð½Ð°ÑĤÑĥÑĢÐ°Ð»ÑĮÐ½

-0.23

POSITIVE LOGITS

ware

0.27

 mechanics

0.26

 rebate

0.26

 voluntary

0.26

 verdict

0.26

merce

0.25

urance

0.25

è³£

0.24

uestas

0.24

mitter

0.24

Activations Density 47.573%

biology, pituitary, medical

No Comments

No Known Activations