© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1737
    Prev
    Next
    INDEX
    Explanations

    [pump] => [pump]

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

    No Comments

    Negative Logits
    泵
    -40.50
     pump
    -39.75
     Pump
    -39.50
     pumps
    -38.50
    水泵
    -29.88
     pumping
    -27.63
     pumped
    -26.38
     pumpkin
    -26.25
     Pap
    -22.00
    MAP
    -21.25
    POSITIVE LOGITS
     Israel
    19.13
    Israel
    18.88
    以色列
    18.50
     android
    17.75
    android
    17.00
     mitochondrial
    16.25
    鞍山
    16.00
    (android
    15.69
    .js
    15.25
     Android
    15.13
    Activations Density 0.042%

    No Known Activations