INDEX

Explanations

followed

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ledged

-0.27

ãİľ

-0.25

 nghiá»ĩp

-0.24

(vp

-0.24

redient

-0.24

Pty

-0.24

.mj

-0.23

åī©

-0.23

ACY

-0.23

 pled

-0.23

POSITIVE LOGITS

 followed

0.88

ä¹ĭåĲİ

0.75

éļıåĲİ

0.68

ç´§æİ¥çĿĢ

0.68

æİ¥çĿĢ

0.64

ä¹ĭå¾Į

0.60

follow

0.59

åĲİéĿ¢

0.58

 thereafter

0.56

 Follow

0.56

Activations Density 0.017%

followed

No Comments

No Known Activations