INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iah

-0.27

ASE

-0.26

ric

-0.26

è¦ģä¸įçĦ¶

-0.26

xmm

-0.25

Ð°ÑĤÐ¾ÑĢ

-0.24

å¾ħ

-0.24

adm

-0.24

æ³¨

-0.24

 collects

-0.24

POSITIVE LOGITS

ãģ°ãģĭãĤĬ

0.27

 Ames

0.27

andles

0.25

eness

0.24

åĳ¼åĴĮ

0.24

iveness

0.24

{i

0.24

åĴ«

0.24

rightness

0.24

 perfection

0.24

Activations Density 0.008%

No Known Activations

This feature has no known activations.