INDEX

Explanations

0

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

flex

-0.28

orr

-0.27

éĹ´æİ¥

-0.27

.".

-0.26

dirs

-0.26

atron

-0.26

icable

-0.25

onga

-0.25

Daemon

-0.24

-flex

-0.24

POSITIVE LOGITS

 Party

0.28

buc

0.25

æģĲ

0.25

è´¨éĩıéĹ®é¢ĺ

0.25

 owners

0.25

ä¸¦ä¸į

0.24

Party

0.24

åĬłå·¥åİĤ

0.24

kn

0.23

 Left

0.23

Activations Density 0.813%

0

No Comments

No Known Activations