INDEX

Explanations

say "to"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ooth

-0.29

—to

-0.29

incerely

-0.26

 Ð¢Ð¾

-0.26

 Toastr

-0.25

icut

-0.25

toi

-0.25

—that

-0.25

.to

-0.24

—which

-0.24

POSITIVE LOGITS

èĲ½åľ¨

0.30

éĽı

0.28

è·ĳ

0.27

æĬµè¾¾

0.27

æ¸ħçĲĨ

0.26

åı¸

0.26

éĺ³

0.26

èĲ½åħ¥

0.26

 prosec

0.25

èĩªåĬ¨

0.25

Activations Density 0.012%

say "to"

No Comments

No Known Activations