INDEX

Explanations

Earth

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 minority

-0.30

ibilit

-0.29

 Minority

-0.28

ibilidad

-0.27

ylvania

-0.26

BufferSize

-0.25

imenti

-0.24

imony

-0.24

æ¯Ķçī¹

-0.24

=""><

-0.24

POSITIVE LOGITS

's

0.32

’s

0.31

Phoenix

0.26

steen

0.25

 stret

0.25

worm

0.25

-history

0.24

çļĦæĸĩåŃĹ

0.24

_lit

0.24

urch

0.23

Activations Density 0.044%

Earth

No Comments

No Known Activations