INDEX

Explanations

Previously, already, currently

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

é©¿

-0.26

 Venue

-0.24

æīįä¼ļ

-0.24

ä¹Łå¥½

-0.23

ablish

-0.23

idge

-0.23

Åĵur

-0.23

ç§ĳåŃ¦çłĶç©¶

-0.23

çĿĩ

-0.23

ernal

-0.22

POSITIVE LOGITS

 joined

0.30

joined

0.28

 Lazy

0.26

èĵį

0.26

[NUM

0.26

lazy

0.26

æĪĲä¸ºä¸ĢåĲį

0.26

nemonic

0.26

eneration

0.25

 joins

0.25

Activations Density 0.005%

Previously, already, currently

No Comments

No Known Activations