INDEX

Explanations

1

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

elp

-0.27

éĻ¢

-0.26

Ð½Ñı

-0.26

 toned

-0.26

ä¸ĢèĪ¬

-0.25

 generally

-0.24

/errors

-0.24

å¯¹æĬĹ

-0.24

æĬĺæī£

-0.24

Ð¾ÑģÑĮ

-0.23

POSITIVE LOGITS

 hist

0.28

reas

0.28

 Lehr

0.26

 psychologist

0.26

Ð¼Ð°ÑĤÐµÑĢÐ¸Ð°Ð»

0.25

 psychologists

0.25

åĵĴ

0.24

dbName

0.24

å¼ģ

0.24

 smith

0.23

Activations Density 0.078%

1

No Comments

No Known Activations