INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÑģÑĤÐ°Ð½Ð°Ð²Ð»Ð¸

-0.27

stops

-0.27

åģľ

-0.26

 ness

-0.26

 stops

-0.25

åģľè½¦

-0.25

è®¤çŁ¥

-0.25

ä½ľé£İ

-0.24

ç¨İ

-0.24

åĬłæ·±

-0.24

POSITIVE LOGITS

 bead

0.28

 exercise

0.26

 trickle

0.26

 place

0.25

 chuck

0.25

Exercise

0.24

ä¸įå¿ħ

0.24

 designs

0.24

æĪĹ

0.24

ä¼

0.23

Activations Density 26.034%

No Known Activations

This feature has no known activations.