INDEX

Explanations

dealing with code/strings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 peas

-0.28

ç«ŀäºīä¼ĺåĬ¿

-0.27

æĸĩåĮĸå»ºè®¾

-0.26

é¹ħ

-0.26

 Culture

-0.25

èĹķ

-0.25

.mainloop

-0.25

onaut

-0.25

ä¹Ĵ

-0.25

zes

-0.25

POSITIVE LOGITS

-li

0.28

Ħ

0.27

STANCE

0.26

romatic

0.25

emo

0.25

allest

0.24

ä»£çĲĨäºº

0.24

åģļä¸įåĪ°

0.24

&R

0.24

 onDelete

0.24

Activations Density 0.005%

dealing with code/strings

No Comments

No Known Activations