INDEX

Explanations

n

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

char

-0.27

lsen

-0.26

 char

-0.26

Å¡ÃŃ

-0.26

OLON

-0.26

èıĸ

-0.25

åĪĨåĪ¥

-0.25

èĬ¬

-0.24

 Eventually

-0.24

ç»§

-0.23

POSITIVE LOGITS

åĽ¢ä½ĵ

0.29

/trunk

0.28

åħ¬ç½ĳ

0.27

ANGE

0.26

 outward

0.25

æ±²

0.25

çĬ

0.25

ç²¾åĬĽ

0.24

Ð°Ð

0.24

NT

0.24

Activations Density 0.018%

n

No Comments

No Known Activations