INDEX

Explanations

atri

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ree

-0.32

åģļå¾Ĺ

-0.27

 Ã§e

-0.26

unic

-0.26

è¿ĲåĬ¨

-0.26

çĽĸ

-0.25

Ñĩ

-0.25

amber

-0.25

 operation

-0.25

erness

-0.25

POSITIVE LOGITS

itemid

0.28

 Banner

0.27

finalize

0.26

 finalize

0.26

 dÃ©part

0.24

 pItem

0.24

çºµæ¨ª

0.24

Æ°á»¡ng

0.23

 itemName

0.23

Synopsis

0.23

Activations Density 39.188%

atri

No Comments

No Known Activations