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

ymes

-0.30

ego

-0.30

ynos

-0.29

ively

-0.28

æľīå¤ļ

-0.27

 seats

-0.24

ValueCollection

-0.24

 Deals

-0.24

 Concent

-0.24

ures

-0.23

POSITIVE LOGITS

éģ£

0.34

[source

0.26

åĴĮå¹³

0.25

å®ŀè´¨æĢ§

0.25

istrict

0.24

andin

0.23

 breadcrumbs

0.23

currentColor

0.23

perimental

0.23

ÑĤÐµÐº

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.