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

ç¬¼ç½©

-0.28

 incident

-0.27

man

-0.26

æİĺ

-0.25

bul

-0.25

sku

-0.25

_man

-0.24

tip

-0.24

Man

-0.24

bul

-0.24

POSITIVE LOGITS

åıĳå±ķçļĦ

0.28

çĶŁäº§çļĦ

0.28

 watched

0.27

åħ¬å®īå±Ģ

0.26

 waterfall

0.25

 drawn

0.24

nip

0.24

èķ²

0.24

-alone

0.24

è§ĦåĪĴè®¾è®¡

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.