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

rec

-0.30

Ars

-0.26

 alone

-0.25

Ð»Ð¸Ð²

-0.25

ial

-0.25

çļĦä¾ĭåŃĲ

-0.25

Rec

-0.25

ç¿°

-0.25

Snake

-0.24

Franc

-0.24

POSITIVE LOGITS

edin

0.30

akov

0.26

 authorised

0.26

ardu

0.25

erca

0.25

çĴİ

0.24

 sinon

0.24

 Mandal

0.24

 concerning

0.24

NonNull

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.