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

ãĤ·ãĥ¥

-0.31

ÑĤÐ¾Ð»

-0.30

å²¸

-0.27

 piled

-0.25

urg

-0.25

mag

-0.25

.tom

-0.25

çĽĤ

-0.24

ä¸Ŀä¸Ŀ

-0.24

æĲĶ

-0.24

POSITIVE LOGITS

æµ·æ´ĭ

0.63

sea

0.60

 ocean

0.55

å¤§æµ·

0.53

æµ·

0.52

 oceans

0.51

 Ocean

0.44

 marine

0.44

sea

0.43

Sea

0.42

Activations Density 0.000%

No Comments

No Known Activations