INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

wap

-0.34

prop

-0.30

äºĭä¸ļåįķä½į

-0.30

 prop

-0.30

gb

-0.28

YN

-0.27

Wi

-0.26

Ups

-0.26

VM

-0.26

umn

-0.25

POSITIVE LOGITS

/operator

0.29

eyer

0.28

istik

0.27

SCAN

0.25

_extent

0.25

.jsx

0.25

 lyrics

0.25

 Ð½Ð°ÑĢ

0.24

åħīå½±

0.24

scan

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.