© 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. 14437
    Prev
    Next
    INDEX
    Explanations

    say arrows

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

    No Comments

    Negative Logits
    yon
    -22.00
     Leone
    -21.25
     Eaton
    -20.13
    奥巴
    -19.75
     Cameron
    -18.25
     Hasan
    -17.50
    ean
    -17.38
     Herman
    -17.25
     Leon
    -17.00
    eon
    -17.00
    POSITIVE LOGITS
    狱
    21.50
    粟
    20.75
    immel
    20.00
     prick
    19.63
    ENCY
    19.50
    indh
    19.50
    vince
    18.50
     Flint
    18.13
    FRING
    18.13
    vy
    18.00
    Activations Density 1.254%

    No Known Activations