INDEX

Explanations

ar

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

 ostr

-0.30

FromArray

-0.27

cs

-0.27

 libr

-0.25

 process

-0.25

 intermediary

-0.25

 depress

-0.24

æŀķå¤´

-0.24

ENN

-0.24

process

-0.24

POSITIVE LOGITS

claimer

0.28

AMPL

0.27

æĢ»çļĦ

0.25

rollable

0.25

æĪİ

0.25

ķĮ

0.24

Ø¨Ø§ØŃ

0.24

 Ã¡ll

0.24

å¤ĸåĮħ

0.24

orang

0.23

Activations Density 4.474%

ar

No Comments

No Known Activations