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

 particular

-0.31

çī¹åĪ«

-0.29

æī¿

-0.27

è¾ħ

-0.26

å°±åı¯ä»¥äºĨ

-0.26

own

-0.25

 provision

-0.25

æĽ¿

-0.25

å¾Īå°ı

-0.24

 post

-0.24

POSITIVE LOGITS

Night

0.29

andr

0.28

 unintention

0.27

åħļç»Ħä¹¦è®°

0.25

æ³ª

0.25

ç½ĳè´Ń

0.25

ASIC

0.24

ä¸įåĥı

0.24

outputs

0.24

edList

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.