INDEX

Explanations

Academic/scientific texts

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

èł¢

-0.27

æį®æŃ¤

-0.27

ä¾§éĩį

-0.26

çĹĽ

-0.26

èµŀåĬ©

-0.25

é³Ŀ

-0.25

æĭİ

-0.24

çĨŁçŁ¥

-0.24

ignore

-0.24

 inspired

-0.24

POSITIVE LOGITS

pel

0.30

pel

0.27

<small

0.26

foy

0.26

 Remaining

0.25

plates

0.25

ENUM

0.25

æ¹ĺè¥¿

0.24

nement

0.24

#:

0.24

Activations Density 27.362%

Academic/scientific texts

No Comments

No Known Activations