INDEX

Explanations

Logical "and" and "or"

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çıįçıł

-0.27

çķĮç¬¬ä¸Ģ

-0.26

",-

-0.24

Sey

-0.24

áº¯ng

-0.24

 dÃ©cision

-0.24

èĦı

-0.23

æ¼Ķåĳĺ

-0.23

.Constant

-0.23

 boring

-0.23

POSITIVE LOGITS

çķ¥

0.28

ATALOG

0.27

èĿĹ

0.27

ICE

0.27

strategy

0.27

 Strategy

0.26

 League

0.26

 neighbors

0.26

 strategy

0.26

 Board

0.26

Activations Density 24.720%

Logical "and" and "or"

No Comments

No Known Activations