INDEX

Explanations

cost

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

issen

-0.31

åľ°ä¸Ń

-0.28

arah

-0.26

Orr

-0.26

 Territory

-0.25

ibi

-0.25

itest

-0.25

otty

-0.25

 tying

-0.25

tie

-0.25

POSITIVE LOGITS

åħ¨å¹´

0.27

æµ£

0.26

æ³¨åĨĮ

0.26

èµĽåŃ£

0.26

æľ¬èµĽåŃ£

0.25

 Studios

0.25

_UNDEFINED

0.25

çĸ¬

0.24

 StreamReader

0.24

 complete

0.24

Activations Density 0.007%

cost

No Comments

No Known Activations