INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

å®īåħ¨æĢ§

-0.28

æ²³è¾¹

-0.26

à¸©à¸²

-0.24

 Flint

-0.24

ockets

-0.24

ering

-0.24

-pocket

-0.23

 discrimin

-0.23

FLOAT

-0.23

éļ¾è¿ĩ

-0.23

POSITIVE LOGITS

è´±

0.24

.setCharacter

0.24

vil

0.24

PROP

0.23

 sounding

0.23

ime

0.22

åĲĦæł·

0.22

Gi

0.22

.put

0.22

éĤ£äºĽ

0.22

Activations Density 0.020%

No Known Activations

This feature has no known activations.