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

æ·ĸ

-0.32

 Fluent

-0.30

çļĦèº«ä»½

-0.29

ifes

-0.28

fern

-0.27

åı¯æĥ³

-0.25

 KIND

-0.24

 Maid

-0.24

Dire

-0.24

éĻªä½ł

-0.24

POSITIVE LOGITS

åħ±é¸£

0.28

ount

0.27

ily

0.26

éĢļ

0.26

 btnSave

0.26

atz

0.24

ising

0.24

iy

0.24

áŀ¶áŀ

0.24

åĪĽå§ĭ

0.24

Activations Density 0.019%

No Known Activations

This feature has no known activations.