INDEX

Explanations

code/technical documents

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æľ¬æ¬¡

-0.42

è¿Ļæ¬¡

-0.39

æŃ¤æ¬¡

-0.36

æľ¬æ¬¡æ´»åĬ¨

-0.35

ä»ĬåĽŀ

-0.34

ä»ĬåĽŀãģ¯

-0.33

éĢĻæ¬¡

-0.32

æľ¬æ¡Ī

-0.31

ä»ĬåĽŀãģ®

-0.31

æľ¬åľºæ¯ĶèµĽ

-0.30

POSITIVE LOGITS

fits

0.27

 BÃ¡o

0.26

hir

0.25

ropsych

0.25

ESIS

0.25

çº¢æĺŁ

0.25

 absolut

0.25

JsonValue

0.24

çľĭä½ł

0.24

(('

0.24

Activations Density 36.672%

code/technical documents

No Comments

No Known Activations