INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lÃ¼

-0.28

bows

-0.28

_frm

-0.26

mÃ¼

-0.25

lude

-0.25

relude

-0.25

ateg

-0.24

 Designed

-0.24

harma

-0.24

lus

-0.23

POSITIVE LOGITS

acle

0.27

åĬ¨æīĭ

0.27

sap

0.26

è±¸

0.26

ä¾ĭè¡Į

0.25

icular

0.24

å²ģæĹ¶

0.24

ous

0.24

Kar

0.24

 symbol

0.24

Activations Density 0.051%

No Known Activations

This feature has no known activations.