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

åĬ³

-0.32

åħ³éĶ®æĺ¯

-0.28

Pru

-0.27

è®¤çľŁ

-0.26

 carries

-0.25

æ¯ķä¸ļ

-0.25

éļ¾

-0.24

ansa

-0.24

heck

-0.24

åħ¶å®ŀæĺ¯

-0.24

POSITIVE LOGITS

 kÄ±sa

0.27

ellers

0.27

ä¾¿åĪ©

0.26

ForRow

0.26

elry

0.26

 flip

0.25

urs

0.25

lÃ¶s

0.24

 accommodating

0.24

 Friedman

0.24

Activations Density 0.012%

of

No Comments

No Known Activations