© 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. 14188
    Prev
    Next
    INDEX
    Explanations

    [Golden] => [B]

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

    No Comments

    Negative Logits
    模型
    -35.25
     model
    -34.00
    model
    -31.50
     модель
    -31.50
    Model
    -31.13
     Model
    -31.13
    モデル
    -30.88
     models
    -30.13
    _model
    -29.88
    	model
    -29.25
    POSITIVE LOGITS
    access
    17.88
     Access
    17.75
     access
    17.75
     accesses
    17.00
    .access
    16.50
    访问
    16.50
    (access
    16.25
     accessor
    15.94
    /access
    15.50
    _access
    15.31
    Activations Density 0.819%

    No Known Activations