INDEX

Explanations

keep

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olini

-0.27

-www

-0.25

_NEED

-0.25

èĥĮä¸Ĭ

-0.25

 adopt

-0.24

 eget

-0.24

rush

-0.24

 ethanol

-0.24

ç«ĭåį³

-0.23

 again

-0.23

POSITIVE LOGITS

ä¿ĿæĮģ

0.38

ä¿ĿæĮģçĿĢ

0.29

keep

0.28

åĲĦå®¶

0.28

 Keep

0.27

 Mojo

0.26

ç¥ŀç§ĺ

0.26

çķĻä½ı

0.26

 Sundays

0.25

 keep

0.25

Activations Density 0.018%

keep

No Comments

No Known Activations