© 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. 14172
    Prev
    Next
    INDEX
    Explanations

    say platform

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

    No Comments

    Negative Logits
    控制系统
    -18.50
    调
    -17.13
     control
    -16.88
    Protection
    -16.50
    _control
    -16.50
    控制
    -16.50
    _Control
    -16.38
    (control
    -16.25
    Control
    -16.13
    控
    -15.88
    POSITIVE LOGITS
    平台
    21.00
    _platform
    20.00
     platform
    20.00
     platforms
    19.75
    _PLATFORM
    19.38
    平台上
    18.88
    Platform
    18.88
     executions
    18.75
    (platform
    18.75
    platform
    18.38
    Activations Density 0.593%

    No Known Activations