INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

QUI

-0.26

andler

-0.25

æī³

-0.25

èĬĤæ°´

-0.25

 Photographer

-0.24

bri

-0.24

 Fram

-0.24

erator

-0.24

(Photo

-0.24

 CALLBACK

-0.24

POSITIVE LOGITS

orb

0.28

å´Ĩ

0.28

è¶Ĭå¥½

0.27

ÑĢÐ¾Ð³

0.26

-gap

0.26

 blanket

0.24

piv

0.24

os

0.24

 Orion

0.24

à§İ

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.