INDEX

Explanations

code, technical documentation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¡ĮåĪĹ

-0.31

aal

-0.29

fleet

-0.28

 folder

-0.27

äºĮèĢħ

-0.27

otre

-0.26

åľ¨å¤ĸ

-0.25

folder

-0.25

çĽ²çĽ®

-0.25

 appear

-0.25

POSITIVE LOGITS

ÅĽci

0.31

structors

0.30

 fixtures

0.30

ctions

0.30

 selectors

0.30

 wallpapers

0.29

 vouchers

0.29

 examples

0.28

uments

0.28

 poems

0.28

Activations Density 0.014%

code, technical documentation

No Comments

No Known Activations