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

æ´µ

-0.25

 contra

-0.25

 forwards

-0.23

 interview

-0.23

ģ

-0.23

 Knot

-0.23

 specification

-0.23

 gate

-0.23

æĸ°åħ´äº§ä¸ļ

-0.23

asca

-0.23

POSITIVE LOGITS

emble

0.32

esModule

0.27

æĪĲéķ¿

0.27

ç»ĻäºĪäºĨ

0.27

åĲĮæł·æĺ¯

0.27

åºķæ°Ķ

0.26

AxisAlignment

0.24

tti

0.24

æķĻè®Ń

0.24

omes

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.