© 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. 15223
    Prev
    Next
    INDEX
    Explanations

    say 革命

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

    No Comments

    Negative Logits
    eworthy
    -19.63
    ATORY
    -19.38
    edException
    -18.88
    ogne
    -18.38
    usband
    -17.38
    isse
    -17.25
    ensing
    -17.25
    舒服
    -17.13
    ToPoint
    -16.88
    家住
    -16.63
    POSITIVE LOGITS
    (history
    15.19
    history
    14.63
     history
    14.63
    历史
    14.00
     History
    13.88
    histoire
    13.75
    flow
    13.69
    质
    13.38
     Hist
    13.31
    .history
    12.88
    Activations Density 0.092%

    No Known Activations