INDEX

Explanations

Action verbs/activities

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

ler

-0.26

 Attachment

-0.24

åĪĨæľŁ

-0.24

 attachment

-0.24

 attachments

-0.23

Fault

-0.23

acity

-0.23

æĬ½æ£Ģ

-0.23

uster

-0.23

der

-0.23

POSITIVE LOGITS

obuf

0.28

Ð°Ð»ÑĮ

0.27

ä¹Łå°±

0.24

idores

0.24

bps

0.24

platz

0.24

<![

0.24

 vero

0.24

stinian

0.24

ç½¨

0.23

Activations Density 0.006%

Action verbs/activities

No Comments

No Known Activations