INDEX

Explanations

that

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

åŁİå¸ĤçļĦ

-0.28

 terme

-0.28

cube

-0.27

æĢİæł·

-0.26

æ¹ĸ

-0.25

åĹ¤

-0.25

á»ĳc

-0.25

alyze

-0.24

allee

-0.24

alon

-0.24

POSITIVE LOGITS

bugs

0.27

bes

0.26

è²Į

0.25

.MEDIA

0.24

è´¹

0.24

abouts

0.24

 movements

0.24

roups

0.24

 masses

0.23

idges

0.23

Activations Density 0.003%

that

No Comments

No Known Activations