INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 minds

-0.29

 mind

-0.27

 serialVersionUID

-0.26

(process

-0.25

press

-0.25

è´¨éĩıéĹ®é¢ĺ

-0.24

pz

-0.24

Mind

-0.24

è¿Ļä¸ªéĹ®é¢ĺ

-0.23

çĶ¨æĪ·æıĲä¾Ľ

-0.23

POSITIVE LOGITS

 therein

0.28

æĻ¦

0.25

èĪĴ

0.25

ein

0.24

enuous

0.24

etting

0.24

 recommending

0.24

æĪ¢

0.24

ä¸įå¤ļ

0.23

Deferred

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.