© 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. 1943
    Prev
    Next
    INDEX
    Explanations

    [country] => [country]

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

    No Comments

    Negative Logits
    艺术
    -17.88
    olicies
    -17.50
    Javascript
    -17.25
     law
    -16.63
    mail
    -15.69
    经济
    -15.19
    erty
    -15.13
     laws
    -15.06
     art
    -14.75
    Email
    -14.44
    POSITIVE LOGITS
     Huss
    18.88
     Compound
    17.63
    compound
    17.38
     Auditor
    17.00
     compound
    17.00
    quat
    16.88
     Agu
    16.88
    发言人
    16.38
     Audi
    16.25
    stoff
    15.88
    Activations Density 0.133%

    No Known Activations