© 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. 14419
    Prev
    Next
    INDEX
    Explanations

    Sir

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

    No Comments

    Negative Logits
    cone
    -23.38
    -Con
    -22.25
    con
    -20.88
    _conv
    -20.38
     Con
    -20.13
    .con
    -19.75
     con
    -19.63
    conv
    -19.50
    -con
    -19.50
    cons
    -19.25
    POSITIVE LOGITS
    TickCount
    15.69
    iap
    15.44
    inspace
    15.38
    浞
    14.31
     xuyên
    14.25
     fingert
    14.19
    iado
    13.94
     Stück
    13.94
    stück
    13.94
     darn
    13.75
    Activations Density 0.525%

    No Known Activations