INDEX

Explanations

tools

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

ByVersion

-0.31

¢åįķ

-0.26

æļ¹

-0.25

½æķ°

-0.25

ByUrl

-0.25

nqu

-0.24

quist

-0.24

 Coke

-0.24

WindowSize

-0.24

ubbles

-0.23

POSITIVE LOGITS

éļĲå½¢

0.29

åĲ«

0.27

 genu

0.27

ido

0.27

idon

0.27

olas

0.26

æł¼å°Ķ

0.25

ionic

0.25

 concealed

0.25

 invent

0.25

Activations Density 0.000%

tools

No Comments

No Known Activations