INDEX

Explanations

scientific studies

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

ä¸Ģç«Ļ

-0.27

 Ling

-0.26

iors

-0.26

UNK

-0.25

åŃ©

-0.25

 uncertainties

-0.25

-relative

-0.25

erson

-0.25

ĮĢ

-0.24

 dues

-0.24

POSITIVE LOGITS

 Compound

0.25

éĤ£æ¬¡

0.25

ç£´

0.25

éĤ£ä¸Ģ

0.24

Compound

0.24

åħĶ

0.24

roys

0.23

ucht

0.23

obel

0.23

Those

0.23

Activations Density 0.001%

scientific studies

No Comments

No Known Activations