INDEX

Explanations

of

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

-mask

-0.28

 mask

-0.28

 referees

-0.27

 masking

-0.26

 referee

-0.26

 refere

-0.26

pio

-0.25

èī²å½©

-0.25

.mask

-0.25

Msp

-0.25

POSITIVE LOGITS

WL

0.30

XL

0.28

iec

0.27

Flo

0.26

 Å»

0.26

è°Ľ

0.25

ä¹ŁçŁ¥éģĵ

0.25

æĬķ

0.25

WX

0.24

XL

0.24

Activations Density 0.080%

of

No Comments

No Known Activations