© 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. 14253
    Prev
    Next
    INDEX
    Explanations

    say image

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

    No Comments

    Negative Logits
    系统
    -46.25
    系统的
    -43.75
     system
    -42.00
     systems
    -41.50
    system
    -40.00
     System
    -39.00
    systems
    -39.00
    _system
    -38.25
     Systems
    -38.00
    -system
    -38.00
    POSITIVE LOGITS
    策略
    15.13
    osition
    14.50
    aData
    14.19
     images
    13.94
     position
    13.94
     solution
    13.81
    asurable
    13.81
     solutions
    13.75
     queried
    13.69
    的形象
    13.69
    Activations Density 0.935%

    No Known Activations