© 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. 14486
    Prev
    Next
    INDEX
    Explanations

    person names

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

    No Comments

    Negative Logits
    spath
    -20.13
     Spar
    -20.00
     Barn
    -19.25
    藩
    -19.13
    mlin
    -19.13
     pnl
    -19.00
    普
    -18.38
    pson
    -18.00
    spar
    -17.75
    ewn
    -17.75
    POSITIVE LOGITS
    蚂蚁
    19.50
     Nguy
    18.25
     geg
    18.25
    oyer
    18.13
    ROY
    17.25
    翟
    17.00
    UCT
    16.75
    quete
    16.63
    quet
    16.50
    丐
    16.50
    Activations Density 1.025%

    No Known Activations