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

ylon

-0.28

é¥¯

-0.28

 lacking

-0.28

resas

-0.26

resh

-0.25

éľ°

-0.24

å½ķçĶ¨

-0.23

ç¼ºå°ĳ

-0.23

MLS

-0.23

ndef

-0.23

POSITIVE LOGITS

æ½ľ

0.28

ä¼ĺ

0.28

æ®Ĭ

0.25

eti

0.24

ä¸įå®Į

0.24

spinner

0.24

äºĮåįģå¹´

0.23

 spinner

0.23

ä¸įæĪĲ

0.23

Ð¸Ð²Ð°

0.23

Activations Density 41.451%

No Known Activations

This feature has no known activations.