INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

 Reason

-0.28

chos

-0.25

æĭħ

-0.25

è¢Ĵ

-0.25

æµģæ·Į

-0.25

<select

-0.24

 sequelize

-0.24

selectors

-0.24

 Hilfe

-0.24

Reason

-0.24

POSITIVE LOGITS

Unary

0.27

æĥķ

0.26

 gamm

0.25

åĨħçļĦ

0.25

ãģĬãģı

0.24

ofile

0.24

/of

0.24

 gains

0.24

åģļåĪ°äºĨ

0.24

éĹ¨çªĹ

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.