INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĴ±

-0.26

æ©Łæ§ĭ

-0.25

kar

-0.25

æľºæŀĦ

-0.24

å±ĭ

-0.24

Ã³logo

-0.24

 organizer

-0.23

åºĶçĶ¨

-0.23

ok

-0.23

é¥¯

-0.23

POSITIVE LOGITS

çī²

0.28

-directed

0.27

boro

0.27

éĥ¨

0.26

/terms

0.25

æĶ¾å¿ĥ

0.25

éĥ¨èĲ½

0.25

èĭ

0.25

ielding

0.25

leveland

0.24

Activations Density 0.072%

No Known Activations

This feature has no known activations.