INDEX

Explanations

and

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

ä¸įå¤§

-0.28

-commit

-0.26

åŃĲå¼¹

-0.26

æĿ¾å¼Ľ

-0.25

 Transactions

-0.25

æĪ´

-0.25

äººæ°ĳå¸ģ

-0.24

æĶ¾æĿ¾

-0.24

 relaxation

-0.24

commit

-0.24

POSITIVE LOGITS

ç¼¯

0.29

ensen

0.27

marine

0.26

å¥Ħ

0.26

 disen

0.25

åıĳåĩº

0.25

petto

0.25

æŁĲ

0.25

 oceans

0.24

æı

0.24

Activations Density 0.002%

and

No Comments

No Known Activations