INDEX

Explanations

Definitions and explanations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tamil

-0.29

ially

-0.27

éĿ¢ä¸Ĭ

-0.26

å¥

-0.25

åĲįå£°

-0.25

utral

-0.25

-original

-0.24

å·²ä¹ħ

-0.24

åħ¨æĹ¥

-0.24

gal

-0.24

POSITIVE LOGITS

æĶ¾

0.28

icks

0.26

cover

0.26

éĢıæ°Ķ

0.24

mant

0.24

è½¬è½½

0.24

æĮ¹

0.23

 resultant

0.23

.decorate

0.23

 sost

0.23

Activations Density 25.640%

Definitions and explanations

No Comments

No Known Activations