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

å¨ĺ

-0.29

è°Īè°Ī

-0.27

","");↵

-0.25

strument

-0.25

olio

-0.25

Ð¼ÐµÑĢ

-0.25

å¼Ħ

-0.25

åĨ¥

-0.25

inis

-0.24

xit

-0.24

POSITIVE LOGITS

 veins

0.28

en

0.28

ub

0.28

enan

0.25

 greatly

0.25

å¤§å¹ħ

0.24

è½¶

0.24

ello

0.23

åĩıåĢ¼

0.23

on

0.23

Activations Density 0.085%

No Known Activations

This feature has no known activations.