INDEX

Explanations

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

åı¤ä»Ĭ

-0.29

 paran

-0.26

bli

-0.26

orre

-0.25

 CASCADE

-0.24

DRV

-0.24

 sill

-0.24

 ARGS

-0.23

æľĢåĲĪéĢĤ

-0.23

 designs

-0.23

POSITIVE LOGITS

ãĥªãĥ³ãĤ°

0.33

aging

0.28

 empty

0.27

æľīæĿ¡ä»¶

0.27

cop

0.27

cop

0.26

atum

0.26

.EMPTY

0.25

è´£ç¼ĸ

0.25

_EMPTY

0.24

Activations Density 2.895%

code

No Comments

No Known Activations