© 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. 14100
    Prev
    Next
    INDEX
    Explanations

    say model

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

    No Comments

    Negative Logits
    訴
    -15.25
    报复
    -14.25
    政务
    -13.69
    腥
    -13.50
    ROADCAST
    -13.25
    illin
    -13.06
    裁判
    -13.00
    ioctl
    -12.94
     McCarthy
    -12.94
    复仇
    -12.88
    POSITIVE LOGITS
    模型
    102.00
     model
    96.00
     models
    94.50
    model
    88.50
     Model
    86.50
     Models
    86.00
    モデル
    85.00
    _model
    83.50
    -model
    83.50
    models
    83.00
    Activations Density 2.069%

    No Known Activations