INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

æ´Ĺ

-0.26

éķ¿éĢĶ

-0.25

 discriminator

-0.25

_except

-0.25

æĮĩç¤º

-0.24

 foreigners

-0.24

voy

-0.24

vik

-0.24

æľĢä½³

-0.23

setError

-0.23

POSITIVE LOGITS

åĸĻ

0.28

draul

0.26

åº

0.24

guns

0.24

lia

0.24

 Oliver

0.23

lings

0.23

gun

0.23

ä¾Ŀæ³ķè¿½ç©¶

0.23

hor

0.22

Activations Density 50.351%

No Known Activations

This feature has no known activations.