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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸Ģæīĭ

-0.30

éº»æľ¨

-0.28

æĪĬ

-0.27

çıŃ

-0.26

CMP

-0.26

ibil

-0.26

illow

-0.25

afort

-0.25

 Giles

-0.25

 ReturnType

-0.24

POSITIVE LOGITS

ä¸īå¤§éĺ¶æ®µ

0.30

icas

0.26

$(

0.26

$(

0.25

cury

0.25

oras

0.25

BeforeEach

0.25

cur

0.24

 distinguished

0.24

 multip

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.