INDEX

Explanations

comfort

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

edef

-0.26

elif

-0.26

aland

-0.26

 util

-0.26

åĪ©çĶ¨

-0.26

DA

-0.25

emark

-0.25

æĮģå¹³

-0.25

ely

-0.25

 shar

-0.24

POSITIVE LOGITS

mue

0.31

åĳ¨ä¸Ģ

0.27

ODB

0.27

-sn

0.25

 sovereignty

0.25

brook

0.25

qus

0.24

iete

0.24

seys

0.24

 $('[

0.24

Activations Density 0.017%

comfort

No Comments

No Known Activations