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

éĤł

-0.27

 cooling

-0.26

 race

-0.24

Cool

-0.24

race

-0.24

quis

-0.24

ä¸Ģç¢Ĺ

-0.24

 riders

-0.24

cool

-0.23

VIA

-0.23

POSITIVE LOGITS

 stripper

0.25

 encount

0.24

 erotica

0.23

é«ĺå°Ķ

0.23

 stret

0.23

æīĢè¯´

0.23

Yet

0.23

 Anyway

0.23

ativ

0.22

ä¹Łæĺ¯å¾Ī

0.22

Activations Density 0.001%

No Known Activations

This feature has no known activations.