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

è¢Ń

-0.27

å¯Ĩå°ģ

-0.26

äººçĶŁçļĦ

-0.25

rising

-0.25

ritis

-0.25

æĿĢ

-0.25

 seal

-0.24

 respectively

-0.24

æºĲäºİ

-0.24

å¼ķæĿ¥

-0.24

POSITIVE LOGITS

éĤ£æł·çļĦ

0.31

Vector

0.27

Actor

0.26

éĤ£æł·

0.26

 Cowboy

0.25

Parms

0.25

 Actor

0.25

 Riders

0.24

vector

0.24

PDO

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.