INDEX

Explanations

among

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

among

-0.32

 among

-0.32

 professors

-0.29

 Among

-0.28

getApplication

-0.25

 amongst

-0.24

èĢģå¸Ī

-0.24

 handleMessage

-0.24

Among

-0.24

å·¥äºº

-0.24

POSITIVE LOGITS

åĩłä¸ª

0.47

 several

0.44

åĩł

0.39

å¹¾åĢĭ

0.37

åĩłç§į

0.34

åĩłçĤ¹

0.33

0.32

 Several

0.30

 máº¥y

0.30

ãģĦãģıãģ¤ãģĭ

0.30

Activations Density 0.006%

among

No Comments

No Known Activations