INDEX

Explanations

a

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

Negative Logits

ä¹ĭæĺŁ

-0.27

 Hornets

-0.26

arbon

-0.26

elope

-0.25

rastructure

-0.25

zeÅĽ

-0.24

è½¦ä½į

-0.24

åĩ°

-0.24

ertype

-0.24

ponent

-0.24

POSITIVE LOGITS

åĩłæŃ¥

0.29

MD

0.29

åĪĩæį¢

0.26

ÑĪÐ¸Ð²

0.26

æ´½

0.26

vic

0.25

åĩĨ

0.25

 Tong

0.25

                    ↵                    ↵

0.24

&q

0.24

Activations Density 9.739%

a

No Known Activations