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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

equal

-0.27

äºĮæľŁ

-0.26

<F

-0.25

Redux

-0.25

 Fact

-0.25

 onView

-0.25

Concept

-0.24

etrize

-0.24

---@

-0.24

 Concept

-0.24

POSITIVE LOGITS

oba

0.29

 motivations

0.27

 Crystal

0.26

 hires

0.26

åķĨ

0.25

 rollers

0.25

ä¸įæ¸ħæ¥ļ

0.25

Cr

0.25

cr

0.25

ä¸įå¤Ł

0.25

Activations Density 0.004%

No Known Activations

This feature has no known activations.