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

azio

-0.30

ious

-0.27

 Text

-0.26

 Field

-0.25

 Claw

-0.25

 Prev

-0.24

 entityManager

-0.24

 coinc

-0.24

Mer

-0.24

acional

-0.23

POSITIVE LOGITS

çĶľç¾İ

0.27

åļ

0.26

è¿ĽæĿ¥

0.24

ä»ĬæĹ¥

0.24

punk

0.24

ç¦º

0.24

çİ©å®¶æĿ¥è¯´

0.24

_verify

0.23

å¤ªå¹³æ´ĭ

0.23

Pitch

0.23

Activations Density 0.883%

No Known Activations

This feature has no known activations.