© 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. 14392
    Prev
    Next
    INDEX
    Explanations

    Martin Van Buren

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

    No Comments

    Negative Logits
    imore
    -19.25
    _secure
    -16.00
     Patterson
    -16.00
    INGER
    -15.50
    _gshared
    -15.44
    anch
    -14.88
     ugl
    -14.69
    璋
    -14.31
    apl
    -14.25
    rench
    -14.00
    POSITIVE LOGITS
     di
    28.75
    di
    22.00
     Di
    22.00
    Di
    21.50
     Nap
    21.38
    -di
    20.50
    _di
    20.13
    dí
    20.00
    .di
    19.50
    (di
    19.25
    Activations Density 0.715%

    No Known Activations