INDEX

Explanations

ordinal numbers

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

èµ´

-0.29

æĤ¨å¥½

-0.27

emer

-0.27

åĽłåŃĲ

-0.27

è¿ĲåĬ¨

-0.25

Emer

-0.25

UST

-0.25

çļĦè¶ĭåĬ¿

-0.24

æĸ°éĻĪä»£è°¢

-0.24

CompatActivity

-0.24

POSITIVE LOGITS

award

0.28

Ð¾Ð²Ð°ÑĢ

0.26

ilha

0.24

ãģ¤ãĤĤãĤĬ

0.24

]|

0.24

-option

0.23

endcode

0.23

ancial

0.23

 storyt

0.23

å·´æĭī

0.23

Activations Density 0.047%

ordinal numbers

No Comments

No Known Activations