INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

udging

-0.27

iad

-0.26

atrix

-0.24

åįµ

-0.24

 gamle

-0.24

lap

-0.24

depth

-0.23

 edad

-0.23

 grub

-0.23

owel

-0.23

POSITIVE LOGITS

æĪĲä¸ºä¸ŃåĽ½

0.28

æĪĲäºĨ

0.28

åħ³äºİæĪĳä»¬

0.28

æĪĲäºº

0.27

som

0.27

æĪĲä¸º

0.27

borne

0.25

SOM

0.25

zes

0.24

çľŁçļĦ

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.