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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Minus

-0.27

âĢ¿

-0.26

elah

-0.26

-0.25

plus

-0.25

æŃ¤ä¸¾

-0.25

æīĭæĮĩ

-0.25

ä¸Ģä¸ĭ

-0.25

åĢĴ

-0.24

manÄ±z

-0.24

POSITIVE LOGITS

mc

0.28

 perce

0.27

 techn

0.25

tti

0.25

 consc

0.25

çĨ¨

0.24

MIS

0.24

ObjectContext

0.24

åħ¬ç½ĳå®īå¤ĩ

0.24

 interact

0.24

Activations Density 0.010%

No Known Activations

This feature has no known activations.