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

ķĮ

-0.33

 pNode

-0.28

mig

-0.28

.nodeName

-0.25

 NODE

-0.25

afil

-0.24

onth

-0.24

onso

-0.24

egree

-0.23

åŃ£

-0.23

POSITIVE LOGITS

ä½ı

0.26

ÑĥÐ³Ð»

0.26

åĴĮæĶ¯æĮģ

0.25

æĭ¨

0.24

/uploads

0.24

lobber

0.24

_macro

0.23

 macros

0.23

è±¹

0.23

 upside

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.