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

criptive

-0.30

æĢľ

-0.27

åıĳåħī

-0.27

çĭ¬çī¹çļĦ

-0.27

Photon

-0.25

 mechanically

-0.25

å®ļéĩı

-0.25

dummy

-0.25

 sanctioned

-0.25

(cx

-0.24

POSITIVE LOGITS

 speakers

0.26

 genie

0.25

çļĦä¸»é¢ĺ

0.25

 binding

0.24

éĥ¨éĥ¨éķ¿

0.24

ADB

0.24

AMY

0.24

ivent

0.24

 departments

0.24

come

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.