INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dcc

-0.29

.aspect

-0.27

pkg

-0.25

æľĢé«ĺçļĦ

-0.25

ivel

-0.25

æľĪä¸Ń

-0.25

ÐłÐķ

-0.23

LogLevel

-0.23

åĺĺ

-0.23

åį³æĺ¯

-0.23

POSITIVE LOGITS

æĸ¹åľĨ

0.27

wright

0.26

 forc

0.26

ç§ĳæĬĢå¤§åŃ¦

0.25

 circulated

0.25

lord

0.24

^n

0.24

tod

0.24

rou

0.24

ãĤį

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.