© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2872
    Prev
    Next
    INDEX
    Explanations

    say "ver"

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

    No Comments

    Negative Logits
     Elect
    -18.63
    ví
    -17.88
     genomes
    -17.00
     genome
    -16.50
    帝
    -16.38
     elect
    -15.13
     viruses
    -14.88
    病毒
    -14.63
     CAPITAL
    -14.38
     capital
    -14.19
    POSITIVE LOGITS
     ver
    87.00
     Ver
    86.50
    Ver
    83.50
    (ver
    80.00
    ver
    79.00
    -ver
    72.50
    _ver
    72.00
    .ver
    72.00
    VER
    70.50
     VER
    70.50
    Activations Density 0.261%

    No Known Activations