INDEX

Explanations

Scientific/technical documents

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TargetException

-0.27

oss

-0.27

Gap

-0.27

Jeg

-0.26

åħįè´£å£°æĺİ

-0.26

Gap

-0.25

åħ¼èģĮ

-0.25

åįģäºĮäºĶ

-0.25

.instrument

-0.25

ObjectType

-0.25

POSITIVE LOGITS

seller

0.27

orth

0.26

allon

0.25

æ²¥

0.25

èĪĲ

0.25

è®ºè¿°

0.25

 testimon

0.25

 filthy

0.24

 Flynn

0.24

classified

0.23

Activations Density 0.001%

Scientific/technical documents

No Comments

No Known Activations