INDEX

Explanations

scientific/technical contexts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ordinary

-0.40

 actual

-0.40

å¸¸è§Ħ

-0.39

ä¸ĢèĪ¬çļĦ

-0.36

å¹³æĹ¶

-0.35

æĻ®éĢļçļĦ

-0.34

ordinary

-0.34

 conventional

-0.34

ORMAL

-0.33

çļĦå®ŀéĻħ

-0.33

POSITIVE LOGITS

enga

0.28

éĩįçĤ¹åħ³æ³¨

0.27

æĮģæľīçļĦ

0.26

pto

0.25

amina

0.24

ÑĥÐ»ÑĮÑĤ

0.24

REC

0.23

RICS

0.23

ä¹Łä¸įä¾ĭå¤ĸ

0.23

ensors

0.23

Activations Density 0.013%

scientific/technical contexts

No Comments

No Known Activations