© 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. 14134
    Prev
    Next
    INDEX
    Explanations

    charge

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

    No Comments

    Negative Logits
    设计
    -45.75
     design
    -43.75
    Design
    -40.25
     designs
    -40.00
    設計
    -39.50
     Design
    -39.25
    design
    -39.25
    _design
    -38.50
    设计理念
    -37.25
     designing
    -37.00
    POSITIVE LOGITS
    datable
    14.94
    illard
    14.69
    Callback
    14.63
     carrier
    14.50
     handler
    14.13
    erton
    14.00
    Carrier
    13.94
    ystate
    13.69
    .Callback
    13.56
     Media
    13.38
    Activations Density 0.812%

    No Known Activations