© 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. 2177
    Prev
    Next
    INDEX
    Explanations

    威

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

    No Comments

    Negative Logits
     Pat
    -19.13
    _sem
    -18.75
    .Rec
    -18.63
    UCE
    -17.38
    Phil
    -17.38
     Sem
    -17.25
    Pat
    -17.25
    SEM
    -17.13
     Curry
    -17.13
     patent
    -17.13
    POSITIVE LOGITS
    威
    37.75
     ver
    25.13
    ver
    20.00
    威海
    19.88
    Ver
    19.00
     Ver
    18.75
    (ver
    18.38
     reg
    18.38
    VER
    17.25
    _ver
    17.13
    Activations Density 0.020%

    No Known Activations