INDEX

Explanations

period

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

Negative Logits

rpc

-0.28

oho

-0.26

è°ģ

-0.26

 gÃ³

-0.25

Family

-0.24

ormap

-0.24

 expo

-0.24

_WINDOW

-0.24

åįģåŃĹ

-0.23

 Corinth

-0.23

POSITIVE LOGITS

åı¦ä¸Ģä¸ª

0.35

 another

0.31

åı¦ä¸Ģ

0.30

 Another

0.29

åı¦ä¸Ģç§į

0.28

PIT

0.28

Another

0.27

...č↵

0.27

åĪ¥ãģ®

0.26

(second

0.26

Activations Density 0.004%

period

No Known Activations