INDEX

Explanations

off

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

uards

-0.33

æĺĻ

-0.33

Off

-0.32

/off

-0.29

(off

-0.29

off

-0.29

_off

-0.28

-off

-0.28

off

-0.27

.off

-0.26

POSITIVE LOGITS

æĹłéĻĲ

0.26

ä½¿åĬ²

0.26

anych

0.26

unal

0.24

å±Ī

0.24

++,

0.24

ãĥģãĤ§

0.24

ellar

0.24

Corp

0.23

IBC

0.23

Activations Density 0.114%

off

No Comments

No Known Activations