INDEX

Explanations

of

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

iteit

-0.27

orca

-0.26

Ð°Ð½Ñģ

-0.25

ÙĪØ±ÙĬØ©

-0.25

Eur

-0.24

andr

-0.24

 back

-0.24

losed

-0.24

already

-0.24

ITE

-0.24

POSITIVE LOGITS

åĪĨåĪ«ä¸º

0.28

æĹ¶éĹ´ä¸º

0.26

deo

0.26

åĪĨåī²

0.26

 Â¶

0.26

Rig

0.25

åģ¥åº·æĪĲéķ¿

0.24

 gÃ©n

0.24

bos

0.24

Partition

0.24

Activations Density 0.004%

of

No Comments

No Known Activations