INDEX

Explanations

Ab

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

åģ¥åħ¨

-0.28

 unsett

-0.27

itution

-0.27

rif

-0.27

nim

-0.27

wen

-0.27

Ã±os

-0.25

æŀ¢çº½

-0.25

#End

-0.24

éĻ©

-0.24

POSITIVE LOGITS

 Prelude

0.26

ä¿±

0.25

igg

0.24

 rake

0.24

ãĤ¶

0.24

.nlm

0.24

 geme

0.23

resizing

0.23

XYZ

0.23

çĲĨ

0.23

Activations Density 0.011%

Ab

No Known Activations