INDEX

Explanations

Code/technical writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¹¢

-0.27

éĥģ

-0.26

 differing

-0.26

Ø¯ÙĪØ§

-0.25

rac

-0.25

 getView

-0.24

ãĤīãĤĮãģ¾ãģĻ

-0.24

 intervene

-0.24

compet

-0.24

POSITIVE LOGITS

 considered

0.42

 able

0.41

 evaluated

0.36

 capable

0.36

 unable

0.36

 located

0.33

 positioned

0.33

 classified

0.33

 reviewed

0.31

 drawn

0.31

Activations Density 0.001%

Code/technical writing

No Comments

No Known Activations