INDEX

Explanations

simplification, ease

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

 dÃ©t

-0.26

reading

-0.26

 diff

-0.26

Ĳľ

-0.25

æ»¡äºĨ

-0.25

éĺ´éĺ³

-0.25

å·²ä¹ħçļĦ

-0.24

ISA

-0.24

åħ¨æĺ¯

-0.24

 :-↵

-0.24

POSITIVE LOGITS

åĩºäºİ

0.27

rokes

0.27

bmp

0.26

çĸı

0.26

ãĥļ

0.25

åĵ¡

0.25

ban

0.24

styl

0.24

 batteries

0.24

æįŁå¤±

0.24

Activations Density 6.368%

simplification, ease

No Comments

No Known Activations