INDEX

Explanations

O

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åħ¬

-0.28

æĥħäºº

-0.27

Ð¾Ð·Ð´

-0.26

-tab

-0.24

 detainees

-0.24

affles

-0.24

ç«ĭéĿ¢

-0.23

zÅĳ

-0.23

å»ĵ

-0.23

åħ³æĢĢ

-0.23

POSITIVE LOGITS

å¹´å¹´åºķ

0.27

 targeting

0.26

nels

0.25

çĶŁæķĪ

0.25

...

0.25

-sizing

0.25

Containing

0.24

insic

0.24

çīĽå¸Ĥ

0.24

dden

0.23

Activations Density 7.193%

O

No Comments

No Known Activations