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

lexport

-0.26

åĩºå¢ĥ

-0.24

inal

-0.24

 equipments

-0.23

è¦ĨçĽĸ

-0.23

çļĦåĬªåĬĽ

-0.23

 heaven

-0.23

<&

-0.23

ittings

-0.23

icularly

-0.23

POSITIVE LOGITS

 author

0.26

åıĽ

0.26

å¯¹è¯¥

0.25

éŀĺ

0.25

éĥı

0.25

 strat

0.24

ä¸ªæĢ§

0.24

osph

0.24

çĶ«

0.24

 Authors

0.24

Activations Density 0.015%

No Known Activations

This feature has no known activations.