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

 trÆ°á»Łng

-0.27

à¸Ĭà¸³à¸£à¸°

-0.26

 pros

-0.25

æĪ¿

-0.24

These

-0.24

 Ring

-0.24

abilit

-0.23

.setOn

-0.23

 Mixing

-0.23

 these

-0.23

POSITIVE LOGITS

-UA

0.28

Creators

0.28

entifier

0.26

è¾¹

0.25

éĢłåŀĭ

0.25

ìĬ¤íĬ¸

0.23

çļĦæĥħ

0.23

rar

0.22

 punches

0.22

éħį

0.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.