INDEX

Explanations

to be

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

 power

-0.32

-commit

-0.29

POWER

-0.29

erd

-0.28

 flash

-0.27

raries

-0.26

åĬŁçİĩ

-0.26

 Power

-0.25

çĪ¶

-0.25

 commit

-0.25

POSITIVE LOGITS

mlink

0.30

uco

0.27

ä¸įå¦¨

0.27

 stakeholders

0.26

yen

0.26

phe

0.26

zac

0.26

è¯ķçĿĢ

0.25

ä¸įä¹ı

0.25

ropolis

0.25

Activations Density 0.077%

to be

No Comments

No Known Activations