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

ä¸ºæł¸å¿ĥçļĦ

-0.29

ç¤¾ä¼ļåĮĸ

-0.25

((__

-0.25

.getRow

-0.24

 Sail

-0.24

 third

-0.23

elage

-0.23

Ð°Ð½Ð¸Ñı

-0.23

third

-0.23

 fourth

-0.23

POSITIVE LOGITS

çªį

0.28

æĩĭ

0.27

stick

0.27

opol

0.27

utc

0.26

å¤ļäºĨ

0.26

 hues

0.25

jer

0.25

lei

0.25

sticks

0.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.