INDEX

Explanations

say ".php" or ".html"

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

Negative Logits

-0.31

 even

-0.28

the

-0.28

 gone

-0.27

 with

-0.27

flo

-0.27

æĸĩ

-0.27

*.

-0.26

tan

-0.26

be

-0.25

POSITIVE LOGITS

è¯¥åħ¬åı¸

0.32

è¯¥æĿĳ

0.30

è¯¥æł¡

0.29

.CV

0.28

æĹłæĦı

0.25

è¯¥éĻ¢

0.25

 mileage

0.25

mdir

0.25

inyin

0.24

_tbl

0.24

Activations Density 0.012%

say ".php" or ".html"

No Known Activations