INDEX

Explanations

speed

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

 Radius

-0.29

entine

-0.28

çĥ¦

-0.27

$__

-0.25

Radius

-0.24

 roles

-0.24

*-

-0.23

æ¸¸åĩ»

-0.23

ling

-0.23

->__

-0.23

POSITIVE LOGITS

endency

0.28

etten

0.28

éĴ°

0.26

æĪĳä»¬éĥ½

0.25

ä¾¬

0.24

ilage

0.24

åģľçķĻåľ¨

0.24

IFE

0.24

æ¬¡ãģ®

0.23

æľĿçĿĢ

0.23

Activations Density 0.002%

speed

No Comments

No Known Activations