INDEX

Explanations

private

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĲ¯

-0.29

åĽŀå¤į

-0.29

nal

-0.28

 lies

-0.27

straint

-0.26

 znajdu

-0.25

 oslo

-0.25

ality

-0.25

lie

-0.25

nar

-0.24

POSITIVE LOGITS

 Packing

0.27

Wir

0.27

çĥĽ

0.26

uze

0.26

åĨĻåŃĹæ¥¼

0.26

æĢ¥éĢŁ

0.26

Ware

0.25

é¢Ĩ

0.24

RenderingContext

0.24

oph

0.24

Activations Density 0.005%

private

No Comments

No Known Activations