INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

bru

-0.28

åĲĬ

-0.25

à¸²à¸¢à¸Ļ

-0.25

èŀį

-0.23

ropa

-0.23

åĭĿ

-0.23

è¾¹éĻħ

-0.23

ierge

-0.23

 revoke

-0.23

 syntax

-0.23

POSITIVE LOGITS

åĪĨæķ£

0.26

 Dram

0.25

åĪĻ

0.25

sofar

0.25

lit

0.25

Lit

0.24

 suffering

0.24

 Actors

0.24

ĺè®¤

0.24

mmo

0.24

Activations Density 17.779%

No Known Activations

This feature has no known activations.