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

acea

-0.27

åįģéĩĮ

-0.26

TED

-0.25

esty

-0.24

 motivate

-0.24

 reform

-0.23

rena

-0.23

/drivers

-0.23

 Nickel

-0.23

ocal

-0.23

POSITIVE LOGITS

lots

0.28

controls

0.25

avy

0.25

åĸ³

0.24

Apis

0.24

 whoever

0.24

æ´Ĵ

0.24

èĲ½

0.24

pect

0.24

 ÐºÐ°Ð¿

0.24

Activations Density 0.067%

No Known Activations

This feature has no known activations.