INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zzo

-0.27

ek

-0.25

 appearing

-0.24

 furn

-0.24

ä¾ĭ

-0.24

ochen

-0.24

 spread

-0.24

urv

-0.24

æĤ¨

-0.24

bru

-0.23

POSITIVE LOGITS

anse

0.27

ibile

0.26

æī¹å¤į

0.26

_TM

0.26

â¾

0.25

éĻĦåĬł

0.25

atars

0.24

IDER

0.24

 onsite

0.24

 Shades

0.24

Activations Density 1.689%

No Known Activations

This feature has no known activations.