INDEX

Explanations

lucky

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

imore

-0.29

åĩĨå¤ĩå·¥ä½ľ

-0.28

#@

-0.28

æ°´åŁŁ

-0.27

Ð·Ð¾Ð²

-0.27

ÑĥÑĢÑģ

-0.27

wart

-0.27

ÐļÑĥÑĢÑģ

-0.25

ftware

-0.25

PrototypeOf

-0.25

POSITIVE LOGITS

è¯ļ

0.31

etas

0.26

/gin

0.26

.null

0.25

gist

0.25

 NullPointerException

0.25

èªł

0.23

 leading

0.23

çļĦè¶ĭåĬ¿

0.23

NaN

0.23

Activations Density 0.000%

lucky

No Comments

No Known Activations