INDEX

Explanations

positive sentiment

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 next

-0.32

ä¸ĭä¸Ģ

-0.31

ä¸ĭä¸Ģä¸ª

-0.30

èĺĸ

-0.29

next

-0.29

 nÃ¤ch

-0.27

	next

-0.27

 nÃ¤chsten

-0.27

.–

-0.27

.next

-0.26

POSITIVE LOGITS

 better

0.39

better

0.36

 optim

0.36

optim

0.33

Better

0.33

 best

0.32

esses

0.31

anning

0.28

æĽ´å¥½

0.28

 Better

0.27

Activations Density 0.015%

positive sentiment

No Comments

No Known Activations