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

 Loud

-0.30

hart

-0.27

ç¶ľåĲĪ

-0.26

ourt

-0.25

 inhab

-0.24

 inhabit

-0.24

 GUID

-0.23

/javascript

-0.23

chan

-0.23

eres

-0.23

POSITIVE LOGITS

++

0.25

Ã´m

0.25

includes

0.25

Raises

0.24

omi

0.24

è¯¾æĸĩ

0.24

ç¾İçļĦ

0.24

å·¥ä½ľæĬ¥åĳĬ

0.24

GetEnumerator

0.23

çľģæķĻèĤ²åİħ

0.23

Activations Density 34.301%

No Known Activations

This feature has no known activations.