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

é¢ĳç¹ģ

-0.28

–

-0.27

con

-0.26

VT

-0.26

-0.25

åĨĴ

-0.25

onom

-0.24

åģ¶å°Ķ

-0.24

æĽ´è¦ģ

-0.24

POSITIVE LOGITS

blings

0.28

ç¥ľ

0.26

æĹ¶ä»£ä¸ŃåĽ½

0.25

URRE

0.24

.Unsupported

0.24

()*

0.24

-gnu

0.24

éªħ

0.24

(strict

0.24

<unsigned

0.24

Activations Density 0.006%

No Known Activations

This feature has no known activations.