INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 anchor

-0.27

ä¹³

-0.27

 regeneration

-0.26

ROC

-0.25

uting

-0.25

æĪİ

-0.25

 match

-0.25

match

-0.24

 administration

-0.24

åĳĬ

-0.24

POSITIVE LOGITS

urat

0.29

ç«½

0.26

éĽĢ

0.26

setParameter

0.26

ibaba

0.26

ç½ĳç«Ļåľ°åĽ¾

0.26

ç»Ĭ

0.25

áº¡t

0.25

sets

0.24

æľįåĬ¡æľºæŀĦ

0.24

Activations Density 46.547%

No Known Activations

This feature has no known activations.