INDEX

Explanations

a

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

éĿŀè¦ģ

-0.28

é²¨

-0.27

pitch

-0.27

æĶ¾å®½

-0.27

venes

-0.26

éĢı

-0.25

 relation

-0.25

 pitch

-0.24

Pitch

-0.24

leftrightarrow

-0.24

POSITIVE LOGITS

 Dich

0.27

allah

0.26

cript

0.25

Tpl

0.24

 quoted

0.24

 Styles

0.24

 Locker

0.24

Styles

0.24

 NSURL

0.24

orama

0.23

Activations Density 0.807%

a

No Comments

No Known Activations