INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chia

-0.32

æ°´åĩĨ

-0.28

onica

-0.28

YLE

-0.27

éĤĻ

-0.26

idi

-0.25

moid

-0.25

.nasa

-0.24

åħ¥å¸Ĥ

-0.24

æŀģæĺĵ

-0.24

POSITIVE LOGITS

ISP

0.28

Fre

0.28

omics

0.27

ssp

0.27

MX

0.25

erte

0.24

 Yates

0.23

CTS

0.23

anza

0.23

Sp

0.23

Activations Density 0.046%

No Known Activations

This feature has no known activations.