INDEX

Explanations

Quotations

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

 recip

-0.27

-olds

-0.26

ymph

-0.25

Ã¡b

-0.25

anteed

-0.25

chang

-0.24

æī¬

-0.24

ãģĤãģ¨

-0.24

eah

-0.24

celed

-0.24

POSITIVE LOGITS

æĮĩæłĩ

0.27

ut

0.26

åĳ½åĲįä¸º

0.26

çĸ¯

0.25

ignore

0.25

ç«ĭãģ¡

0.25

éķĤ

0.25

å¯¹äºİ

0.25

cont

0.25

 Born

0.25

Activations Density 11.093%

Quotations

No Comments

No Known Activations