INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ifers

-0.28

ç½ķ

-0.27

rig

-0.27

verb

-0.26

arge

-0.26

 Dead

-0.25

å½

-0.25

IFE

-0.25

Ð³Ð¸

-0.25

 defer

-0.24

POSITIVE LOGITS

äºĶåĪĨéĴŁ

0.26

æł·

0.26

ä¾Ľ

0.25

å¯¹åºĶ

0.25

 aspiring

0.24

ç³»

0.24

çĽĶ

0.23

 Ð´ÐµÑıÑĤÐµÐ»ÑĮ

0.23

å¯¹åºĶçļĦ

0.23

ç»ĻæĪĳ

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.