INDEX

Explanations

technical reports and code

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

IndexOf

-0.29

ÑģÐ¿

-0.27

æľĹ

-0.27

.onNext

-0.26

éķ¿çŁŃ

-0.25

agem

-0.25

ram

-0.25

 Bodies

-0.25

è¿ĩäºĨ

-0.25

#:

-0.24

POSITIVE LOGITS

.cgi

0.33

limited

0.30

izona

0.28

_tolerance

0.27

å¾ħ

0.27

è¿

0.26

 limited

0.26

 Limited

0.26

quals

0.24

åĨįæĿ¥

0.24

Activations Density 0.107%

technical reports and code

No Comments

No Known Activations