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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ïİ

-0.34

åĵ²

-0.30

äº¶

-0.26

brig

-0.26

 Politico

-0.26

phe

-0.25

isode

-0.24

curity

-0.24

çļĦåĽŀçŃĶ

-0.24

ç¤¾ä¼ļæ²»çĲĨ

-0.24

POSITIVE LOGITS

 incumb

0.29

 Success

0.28

.qq

0.28

opup

0.26

FAULT

0.25

.Success

0.25

 success

0.24

 Ceiling

0.24

æĦŁ

0.24

æĪĲåĬŁ

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.