© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1466
    Prev
    Next
    INDEX
    Explanations

    [CC] => [copy]

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

    No Comments

    Negative Logits
    dll
    -22.25
     SS
    -20.75
    SSL
    -20.63
    McC
    -19.75
    _ss
    -19.75
     ll
    -19.38
     McCoy
    -19.38
    /ss
    -18.88
    _bb
    -18.88
    dden
    -18.88
    POSITIVE LOGITS
    中国汽车
    16.38
    泪
    15.81
     EDUC
    14.69
    哭了
    14.31
    lei
    14.31
    教育
    14.25
     educate
    13.94
    IOC
    13.75
    bac
    13.63
     education
    13.56
    Activations Density 0.507%

    No Known Activations