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

æīĢæıĲä¾Ľ

-0.27

 Charl

-0.27

 average

-0.25

 Termin

-0.24

ild

-0.24

ä¼Ĭæĭī

-0.24

ä¹Łåıªæĺ¯

-0.24

fix

-0.24

ossal

-0.24

 arrang

-0.24

POSITIVE LOGITS

å·¦æīĭ

0.30

atern

0.27

ater

0.27

å®¿

0.26

incy

0.26

iors

0.26

ANA

0.26

ameron

0.25

inema

0.25

çĶ¨æīĭ

0.25

Activations Density 0.001%

No Known Activations

This feature has no known activations.