INDEX

Explanations

groupings of items

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

ä¹¦æ³ķå®¶

-0.28

äºµ

-0.28

sprites

-0.27

jab

-0.26

 against

-0.26

è¢«èªīä¸º

-0.26

edar

-0.25

/callback

-0.25

£¼

-0.25

cb

-0.25

POSITIVE LOGITS

æĪĸèĢħåħ¶ä»ĸ

0.29

ArgsConstructor

0.26

 defect

0.25

æĪĸåħ¶ä»ĸ

0.25

æ··ä¹±

0.24

åıĳ

0.24

ä¸Ľ

0.24

æĭ¼éŁ³

0.23

itis

0.23

ç¨ĭ

0.23

Activations Density 0.004%

groupings of items

No Comments

No Known Activations