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

åĨ»

-0.26

asis

-0.26

 frozen

-0.26

åĨ»ç»ĵ

-0.26

('(

-0.25

 bracket

-0.25

XL

-0.25

 prop

-0.25

mob

-0.24

umpy

-0.24

POSITIVE LOGITS

æ³Ħ

0.26

rowable

0.25

à¸£à¸ĩ

0.24

æ³»

0.24

ilha

0.24

 kitchens

0.24

å¹¶åĲĳ

0.24

è´¹

0.24

è°¦

0.24

è·Ħ

0.23

Activations Density 0.005%

No Known Activations

This feature has no known activations.