INDEX

Explanations

at

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

ONO

-0.28

efa

-0.28

åĬŁåĬĽ

-0.27

 segregation

-0.27

hoot

-0.26

 progress

-0.25

stakes

-0.25

pel

-0.25

 Follow

-0.25

 Himself

-0.25

POSITIVE LOGITS

 rate

0.30

éĢŁçİĩ

0.29

æŃ¥ä¼Ĳ

0.29

akter

0.28

éĢŁåº¦

0.28

pace

0.28

rate

0.27

 rates

0.27

 bulund

0.26

_rate

0.26

Activations Density 0.003%

at

No Comments

No Known Activations