© 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. 14556
    Prev
    Next
    INDEX
    Explanations

    童

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

    No Comments

    Negative Logits
     Benton
    -19.50
    เต
    -19.38
    .Stretch
    -17.75
     radiator
    -17.63
     Dil
    -17.63
    атор
    -17.25
    投标人
    -17.25
     Bryant
    -16.88
     Kant
    -16.50
    墙上
    -16.50
    POSITIVE LOGITS
    avo
    19.63
    afia
    18.13
     erv
    17.88
    舸
    17.63
     Vox
    17.50
    ivo
    17.25
    ices
    17.13
    ever
    16.63
    ypy
    16.50
    ipp
    16.38
    Activations Density 0.864%

    No Known Activations