INDEX

Explanations

code, technical documentation

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

ãĥķãĥĪ

-0.29

agrid

-0.27

anya

-0.27

.getConfig

-0.26

ix

-0.25

 explicitly

-0.25

 just

-0.25

çīºçī²

-0.24

atel

-0.24

infeld

-0.24

POSITIVE LOGITS

æ¯Ķäºļ

0.32

avigate

0.27

ÙĨØ§ÙĤ

0.27

endance

0.26

jie

0.26

éķĳ

0.26

å¹´æĿ¥

0.25

å¤ļå¹´æĿ¥

0.25

ä¸»æµģ

0.25

å¹´éĻĲ

0.24

Activations Density 0.152%

code, technical documentation

No Comments

No Known Activations