INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åħ³èģĶäº¤æĺĵ

-0.30

 oppon

-0.27

ä¾ĿéĿł

-0.26

.package

-0.26

ç¬¬ä¸Ģå®¶

-0.26

æł¸å®ļ

-0.25

 Pills

-0.25

geist

-0.24

,{"

-0.24

 questionable

-0.24

POSITIVE LOGITS

rosse

0.28

habi

0.27

reau

0.25

 bright

0.25

+m

0.24

æ²¸

0.24

å¸Ĥ

0.24

æ¨¡æĿ¿

0.24

 templates

0.24

aits

0.24

Activations Density 0.011%

No Known Activations

This feature has no known activations.