INDEX

Explanations

province

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 buckle

-0.30

çīĻ

-0.28

ertia

-0.27

quee

-0.25

åı¯ä»¥è®©

-0.25

.STATE

-0.24

æĮĩæķ°

-0.24

>Title

-0.24

 maxHeight

-0.24

_slope

-0.24

POSITIVE LOGITS

operand

0.26

 Bass

0.25

à¸±à¸ĩ

0.25

UnitOfWork

0.24

 False

0.24

raw

0.24

operator

0.24

raw

0.24

ishes

0.24

 operand

0.24

Activations Density 0.029%

province

No Comments

No Known Activations