© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14131
    Prev
    Next
    INDEX
    Explanations

    legal disclaimer

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     application
    -84.50
    应用
    -82.50
     applications
    -81.00
     Application
    -78.50
    Application
    -75.00
    application
    -74.50
     Applications
    -72.00
    的应用
    -71.50
    applications
    -71.50
    _application
    -71.00
    POSITIVE LOGITS
     Neptune
    13.63
    税费
    13.13
     pł
    12.81
    uling
    12.75
    픽
    12.50
    ogie
    12.13
    悦
    11.75
    辟
    11.75
    讨论
    11.56
    rians
    11.44
    Activations Density 2.333%

    No Known Activations