INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

åıįå¼¹

-0.26

experiment

-0.25

dot

-0.24

enie

-0.24

èķī

-0.24

 há»©ng

-0.23

Ã´n

-0.23

Experiment

-0.23

 Experiment

-0.23

ìħĺ

-0.23

POSITIVE LOGITS

SCP

0.27

ugh

0.27

pch

0.24

perms

0.24

 mates

0.24

åĭĴ

0.24

 leagues

0.23

upal

0.23

uish

0.23

 perms

0.23

Activations Density 0.433%

No Known Activations

This feature has no known activations.