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

Not in Any Lists

No Comments

Negative Logits

æķ´é½Ĳ

-0.28

éķĩ

-0.26

åįģåĪĨ

-0.26

å¸¦

-0.25

é¢ĺ

-0.25

è§ģ

-0.25

åĪ«

-0.24

Inverse

-0.24

éĢīæĭ©

-0.24

å¤ĦçĲĨ

-0.24

POSITIVE LOGITS

 abstraction

0.30

 Merlin

0.29

 exceeded

0.28

 tool

0.25

 qualifies

0.25

 ship

0.25

 abstract

0.25

åĵ¨

0.25

 qualify

0.25

 speculated

0.25

Activations Density 0.001%

No Known Activations

This feature has no known activations.