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

Negative Logits

rous

-0.28

è½

-0.27

è¶Ĭå¥½

-0.25

two

-0.25

erde

-0.25

 sorte

-0.25

pel

-0.23

å¯»å¸¸

-0.23

....↵↵

-0.23

/web

-0.23

POSITIVE LOGITS

Ç¿

0.27

éĹªè¿ĩ

0.25

çŁ³å®¶

0.24

è¥¿äºļ

0.24

udio

0.24

ography

0.24

äº§åľ°

0.23

SessionFactory

0.23

çľĭçĤ¹

0.23

 Crimes

0.23

Activations Density 37.817%

No Known Activations

This feature has no known activations.