INDEX

Explanations

and

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

çĲĨå·¥

-0.27

...",

-0.26

åħ¨å®¶

-0.25

antal

-0.24

æĬĸ

-0.24

 –↵↵

-0.24

 exposures

-0.23

jong

-0.23

æģŃ

-0.23

æķĳæµİ

-0.23

POSITIVE LOGITS

isque

0.29

enko

0.25

æ®µ

0.25

åıĺå½¢

0.25

zag

0.25

åĵŁ

0.25

)f

0.24

 ease

0.23

reg

0.23

>tag

0.23

Activations Density 0.049%

and

No Comments

No Known Activations