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

è¯ħ

-0.25

ç§ī

-0.24

boot

-0.24

roma

-0.23

Boot

-0.23

åħ¬æŃ£

-0.23

":"/

-0.23

 boot

-0.23

æ´»åĬ¨çİ°åľº

-0.23

è¿ĩæĿ¥

-0.23

POSITIVE LOGITS

è¾ĩ

0.30

 Worth

0.27

onders

0.26

 worth

0.25

à¦§

0.24

sing

0.24

nbsp

0.23

 dared

0.23

yard

0.23

Activations Density 0.006%

No Known Activations

This feature has no known activations.