INDEX

Explanations

ref

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

 assignable

-0.29

æ½ľèĥ½

-0.25

 redeem

-0.24

éĢĤåºĶ

-0.24

/contact

-0.24

pay

-0.24

é¼ĵ

-0.23

-pay

-0.23

 Operational

-0.23

Operator

-0.23

POSITIVE LOGITS

 earlier

0.26

ä½ŀ

0.25

endez

0.25

è¿Ļä¸Ģå¹´

0.24

 Auss

0.24

çļĦçľ¼ç¥ŀ

0.24

è®³

0.24

chers

0.24

izz

0.24

 cocktail

0.23

Activations Density 0.002%

ref

No Comments

No Known Activations