INDEX

Explanations

Military conflicts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ä¸įè¦ģå¤ª

-0.29

 bond

-0.27

urity

-0.27

pled

-0.26

éĴĵ

-0.26

éŁ³

-0.26

éĴĹ

-0.25

 Ð¸Ð·Ð²ÐµÑģÑĤ

-0.25

umn

-0.25

-ser

-0.24

POSITIVE LOGITS

 editions

0.36

edition

0.26

 subst

0.26

çīĪ

0.26

 edition

0.25

æľīæĽ´å¥½çļĦ

0.25

/Resources

0.25

(descriptor

0.25

ARB

0.24

deg

0.23

Activations Density 0.004%

Military conflicts

No Known Activations