INDEX

Explanations

computer code/technical language

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç»ĵæĿŁ

-0.90

å®Į

-0.86

å®Įæ¯ķ

-0.81

 finished

-0.80

 finish

-0.80

ç»ĵæĿŁäºĨ

-0.77

å®ĮäºĨ

-0.73

çµĲæĿŁ

-0.72

finish

-0.69

 Finish

-0.68

POSITIVE LOGITS

.tp

0.28

éĥ½ä¸įæķ¢

0.25

ettes

0.25

illery

0.24

eh

0.22

ehr

0.22

elleicht

0.22

zes

0.22

	templateUrl

0.22

erequisite

0.22

Activations Density 0.003%

computer code/technical language

No Comments

No Known Activations