© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1194
    Prev
    Next
    INDEX
    Explanations

    [sensor] => [actuator]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    传感器
    -51.50
     sensor
    -50.00
    Sensor
    -47.75
    sensor
    -47.25
     sensors
    -46.25
     Sensor
    -46.00
    (sensor
    -43.00
    _sensor
    -42.75
     Sensors
    -42.75
     SENSOR
    -40.50
    POSITIVE LOGITS
     Italian
    17.13
    windows
    16.75
    rost
    16.75
    .itemView
    16.75
    UI
    16.00
    台
    15.94
    意大利
    15.94
     windows
    15.50
    台上
    15.31
     Windows
    15.25
    Activations Density 0.107%

    No Known Activations