INDEX

Explanations

code and technical writing

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

Not in Any Lists

No Comments

Negative Logits

çļĦåıĺåĮĸ

-0.29

uela

-0.29

çĸ¾çĹħçļĦ

-0.28

 sá»±

-0.27

 Ð¸Ð·Ð¼ÐµÐ½ÐµÐ½Ð¸Ñı

-0.25

 enlargement

-0.25

 structural

-0.25

nis

-0.25

achment

-0.25

 Structural

-0.25

POSITIVE LOGITS

opr

0.28

 tÃ¡n

0.25

owitz

0.25

æķ£å¸ĥ

0.24

 htmlentities

0.24

sofar

0.23

 sniff

0.23

 WithEvents

0.23

orbit

0.23

.Callback

0.23

Activations Density 0.000%

code and technical writing

No Comments

No Known Activations