INDEX

Explanations

determine

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĮģæľīçļĦ

-0.28

æĭ¿çĿĢ

-0.27

 totaling

-0.27

-cat

-0.25

QWidget

-0.25

ulton

-0.25

alker

-0.25

Aud

-0.24

atable

-0.24

 burg

-0.24

POSITIVE LOGITS

how

0.43

å¦Ĥä½ķ

0.38

å¦Ĥä½ķçľĭå¾ħ

0.36

æĺ¯å¦Ĥä½ķ

0.35

 whether

0.35

æĺ¯åĲ¦ä¼ļ

0.33

æĢİä¹Īæł·

0.33

how

0.33

æĢİæł·

0.33

whether

0.31

Activations Density 0.022%

determine

No Comments

No Known Activations