INDEX

Explanations

No Explanations Found

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

pest

-0.30

é©¿ç«Ļ

-0.29

ä¸įä¾¿

-0.27

voie

-0.27

ash

-0.25

åĵªå®¶

-0.25

kest

-0.25

åħħæ²Ľ

-0.25

Datum

-0.24

metrics

-0.24

POSITIVE LOGITS

ÑĦÐ¸

0.28

enie

0.27

è§Ī

0.27

 Sommer

0.26

 gained

0.24

Alamat

0.24

ä¸ºæł¸å¿ĥçļĦ

0.24

criptions

0.24

ATT

0.23

 disgu

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.