INDEX

Explanations

product availability

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

posites

-0.26

æ¨¡æĭŁ

-0.26

æĢİä¹Īè¯´

-0.25

å¥¹æĺ¯

-0.24

æĢ»èµĦäº§

-0.24

åĪĽå»ºå·¥ä½ľ

-0.24

Lie

-0.23

Simulation

-0.23

 Achievement

-0.23

 simulations

-0.23

POSITIVE LOGITS

 commonplace

0.30

åľ¨çĶŁæ´»ä¸Ń

0.29

arton

0.29

..'

0.27

å¾Īå¿«

0.27

 soon

0.27

å¸Į

0.27

utschen

0.25

éļĽ

0.25

çªĹå¤ĸ

0.25

Activations Density 0.001%

product availability

No Comments

No Known Activations