INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

åı¯æĥ³

-0.27

éļĶ

-0.27

.rar

-0.27

blr

-0.26

Alt

-0.25

 Parcelable

-0.25

chooser

-0.25

enko

-0.25

spot

-0.24

 Gross

-0.24

POSITIVE LOGITS

eu

0.29

0.27

JI

0.26

æĬ¤

0.25

jal

0.25

rol

0.24

(_.

0.24

æķ°çĽ®

0.24

iefs

0.23

ä¿Ŀç®¡

0.23

Activations Density 0.838%

No Known Activations

This feature has no known activations.