INDEX

Explanations

Hacking and software exploits

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤªãĥ³

-0.28

Ont

-0.28

oman

-0.28

ONY

-0.27

è·ŁæĪĳè¯´

-0.27

 forg

-0.26

ewolf

-0.26

å¹³åĿĩæ¯ı

-0.26

.fm

-0.25

-used

-0.24

POSITIVE LOGITS

 Merr

0.27

 MEDIA

0.26

idan

0.25

ç»ĦæĪĲ

0.25

åı£å¾Ħ

0.25

åıĳè¡Į

0.24

 Flat

0.24

æ¨ªåĲĳ

0.24

 bach

0.24

å®£ä¼ł

0.24

Activations Density 0.003%

Hacking and software exploits

No Comments

No Known Activations