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

flows

-0.28

haus

-0.28

flow

-0.27

ISING

-0.27

mel

-0.26

sters

-0.26

 ÐºÐ°Ñĩ

-0.26

èļĮ

-0.24

erw

-0.24

ç®ķ

-0.23

POSITIVE LOGITS

_rt

0.29

 AÃ§

0.25

utch

0.25

Tah

0.24

å¤®

0.24

 Patch

0.24

[cell

0.23

æĸ¹å¼ıè¿Ľè¡Į

0.23

Ð¸Ð¿

0.23

ck

0.23

Activations Density 0.009%

No Known Activations

This feature has no known activations.