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

ancybox

-0.30

open

-0.26

web

-0.25

 open

-0.25

.createServer

-0.24

Open

-0.24

 compact

-0.24

_web

-0.23

 closed

-0.23

web

-0.23

POSITIVE LOGITS

 scorn

0.28

ctica

0.26

ä¾ĭè¡Į

0.26

å±±åĮº

0.26

çģ¾

0.25

 Noticed

0.25

 scar

0.24

ÑħÐ¸

0.24

çģ«çĥ§

0.24

éĻ©

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.