INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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¿ŀäºĳ

-0.27

æĹ¥æĬ¥éģĵ

-0.26

onder

-0.25

ICATION

-0.25

abwe

-0.24

ylation

-0.24

rig

-0.23

Scr

-0.23

-Col

-0.23

 UsersController

-0.23

POSITIVE LOGITS

/cop

0.25

 vivo

0.24

çīºçī²

0.24

åģıå¥½

0.24

éĢļçĶ¨

0.24

è§Ħå®ļ

0.23

 Victim

0.23

åĲĮæĹ¶ä¹Ł

0.23

ModelState

0.23

 Respect

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.