INDEX

Explanations

even

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

éĢīæīĭ

-0.28

è¹¼

-0.28

ä¸Ľ

-0.27

éĦĻ

-0.26

 Apprentice

-0.26

nos

-0.26

AttributeName

-0.24

 snork

-0.24

æ¸¯åĮº

-0.24

 deported

-0.24

POSITIVE LOGITS

 even

0.47

even

0.44

 Even

0.41

Even

0.38

è¿ĺè¦ģ

0.32

è¿ĺ

0.32

 EVEN

0.32

åį³ä½¿

0.31

_even

0.31

è¿ĺå¾Ĺ

0.30

Activations Density 0.011%

even

No Known Activations