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

 cast

-0.32

_abstract

-0.28

erna

-0.27

 Erect

-0.26

ibilit

-0.25

-Ta

-0.25

cast

-0.25

ennie

-0.24

isten

-0.24

ercul

-0.24

POSITIVE LOGITS

 Heads

0.26

Mon

0.25

ç«¯æŃ£

0.25

dos

0.24

æĹĹ

0.24

Pairs

0.24

äºĽä»Ģä¹Ī

0.24

åħ¬

0.24

ding

0.24

åĽº

0.23

Activations Density 0.015%

No Known Activations

This feature has no known activations.