INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_35.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.35.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

æľīæľŁ

-0.25

.–

-0.24

äºĭåħĪ

-0.23

ain

-0.23

enheim

-0.23

 penis

-0.23

 bÃ¨

-0.23

 Â¥

-0.23

 “âĢ¦

-0.23

aim

-0.23

POSITIVE LOGITS

/left

0.25

arily

0.24

è½¬èº«

0.24

çĤ¹å¤ļ

0.24

Ð¾Ð±Ð¾ÑĢ

0.23

ÑıÐµÑĤ

0.23

leen

0.23

cate

0.23

.translate

0.23

ality

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.