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

Not in Any Lists

No Comments

Negative Logits

lig

-0.29

è¶³

-0.28

ÂŃt

-0.28

boats

-0.28

atal

-0.28

-ca

-0.26

æľĢå°ı

-0.26

çĲĨ

-0.26

ç¾İèĤ¡

-0.26

]+\

-0.26

POSITIVE LOGITS

elpers

0.28

 Everywhere

0.26

 AppModule

0.26

 installation

0.25

Life

0.25

ibal

0.25

åĩºè·¯

0.25

è¿Ľä¿®

0.24

 Life

0.24

owie

0.24

Activations Density 0.005%

No Known Activations

This feature has no known activations.