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

nee

-0.27

league

-0.27

 Prot

-0.26

.Prot

-0.26

ä¸Ģç»ı

-0.24

çĶļèĩ³æĺ¯

-0.24

çĽ¸åıį

-0.24

ldb

-0.24

 wanted

-0.24

vs

-0.24

POSITIVE LOGITS

imes

0.30

èĩŃ

0.26

Õ£

0.25

uD

0.25

 cakes

0.24

çĽ

0.24

éļį

0.24

-present

0.24

çķª

0.23

 newIndex

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.