INDEX

Explanations

Locations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.IContainer

-0.27

rok

-0.26

æ²¡éĴ±

-0.25

ukan

-0.25

 **/↵

-0.25

fÃ¼hr

-0.24

".$

-0.24

=<

-0.24

åĲŀ

-0.24

 **/↵↵

-0.23

POSITIVE LOGITS

 Sold

0.31

Oh

0.26

æĻºæħ§

0.26

isman

0.25

 verw

0.25

nees

0.24

unts

0.24

ano

0.24

oves

0.24

è§¦

0.24

Activations Density 0.040%

Locations

No Comments

No Known Activations