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

ozilla

-0.25

ãģ«åħ¥

-0.25

_FREQ

-0.25

éļ¼

-0.24

temps

-0.24

mez

-0.24

GetProcAddress

-0.24

åĸĶ

-0.24

æ·±åħ¥æİ¨è¿Ľ

-0.24

 trÃº

-0.24

POSITIVE LOGITS

roat

0.28

batch

0.28

-largest

0.27

_BATCH

0.27

 Spin

0.25

èĩªæĿ¥

0.25

/ay

0.25

Dia

0.25

æī¹

0.25

_ti

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.