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

//=

-0.26

 level

-0.25

 levels

-0.25

è¾Ľåĭ¤

-0.25

 arithmetic

-0.25

 tats

-0.24

 attr

-0.24

RAW

-0.24

 minus

-0.24

 mentally

-0.24

POSITIVE LOGITS

æºħ

0.26

å®ĹæĹ¨

0.26

åĴı

0.25

åĢ¡

0.25

 brushed

0.25

 Ð¿Ð¾Ð´ÑħÐ¾Ð´

0.25

çĶŁæķĪ

0.24

é¸²

0.24

å²ģä»¥ä¸ĭ

0.24

leet

0.23

Activations Density 0.004%

No Known Activations

This feature has no known activations.