© 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. 14356
    Prev
    Next
    INDEX
    Explanations

    citation numbers

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

    No Comments

    Negative Logits
    wich
    -16.13
    lobber
    -15.38
    岛上
    -15.00
    哪个
    -14.94
     which
    -14.00
    [type
    -13.69
    pio
    -13.69
    岛
    -13.56
    Boom
    -13.13
    [@
    -13.06
    POSITIVE LOGITS
    Contrib
    19.13
    =ax
    17.50
    ="_
    17.13
    筷子
    15.69
    _wheel
    15.19
    قال
    15.00
    ducible
    15.00
    able
    14.94
     Gins
    14.81
    دار
    14.75
    Activations Density 0.039%

    No Known Activations