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

Negative Logits

 institutions

-0.26

emit

-0.25

bot

-0.25

å±Ģéĥ¨

-0.25

æĻķ

-0.25

ä¹Łä¸įæķ¢

-0.24

asp

-0.24

 Institutional

-0.24

åĪ©äºļ

-0.24

yet

-0.23

POSITIVE LOGITS

å¤©çĶŁ

0.31

ount

0.30

foil

0.28

FFECT

0.28

åħ»æĬ¤

0.27

çķĶ

0.26

mutable

0.25

æ³¨åħ¥

0.25

èĥľè´Ł

0.25

Inspectable

0.25

Activations Density 0.008%

No Known Activations

This feature has no known activations.