INDEX

Explanations

General news/blog context

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olvable

-0.27

æĿ¥è®²

-0.25

oS

-0.24

åŁİåĮº

-0.24

eward

-0.24

ying

-0.24

à¸·à¹Ī

-0.24

Readable

-0.24

oin

-0.23

æĿ¥è¯´

-0.23

POSITIVE LOGITS

æ¯¡

0.28

 witnessing

0.27

 Goods

0.27

åĽŀæĥ³

0.25

Constant

0.25

 speculative

0.25

 further

0.24

 Constant

0.23

-letter

0.23

GEN

0.23

Activations Density 0.014%

General news/blog context

No Comments

No Known Activations