INDEX

Explanations

locations

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

Cyr

-0.27

éĶĳ

-0.27

sis

-0.26

 extent

-0.26

raries

-0.26

çĶŁåŃĺ

-0.24

 counting

-0.24

burst

-0.24

 counts

-0.24

Extent

-0.24

POSITIVE LOGITS

DEX

0.31

quina

0.26

ruz

0.26

modo

0.25

ERE

0.25

éºĵ

0.25

aux

0.25

rut

0.24

DisplayName

0.24

esub

0.24

Activations Density 0.839%

locations

No Comments

No Known Activations