© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14836
    Prev
    Next
    INDEX
    Explanations

    printed on

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

    No Comments

    Negative Logits
    .unlink
    -17.00
    clin
    -16.88
     rodents
    -16.63
     Sour
    -16.25
    .balance
    -16.13
    alink
    -16.00
    orz
    -15.81
    жал
    -15.81
     бол
    -15.69
     stretches
    -15.56
    POSITIVE LOGITS
    限量
    13.88
     Tits
    13.06
    ilt
    12.94
    anguard
    12.81
    颁发
    12.69
    /tags
    12.56
    conomy
    12.06
    高价
    11.75
    Own
    11.31
    总监
    11.31
    Activations Density 0.088%

    No Known Activations