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

entes

-0.27

oming

-0.26

 Worcester

-0.25

å·ŀ

-0.25

uning

-0.24

æĽ¼

-0.24

hton

-0.24

wise

-0.24

 Robbie

-0.24

å·ŀå¸Ĥ

-0.23

POSITIVE LOGITS

æ³¡

0.30

ãģ¨ãģĦãģĨãĤĤãģ®

0.27

cmds

0.26

æĮ½

0.25

_triggered

0.24

æļ´éľ²

0.24

åĴĭ

0.23

 trigger

0.23

.Exists

0.23

ãģĭãģĭãĤĬ

0.23

Activations Density 0.053%

No Known Activations

This feature has no known activations.