© 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. 1185
    Prev
    Next
    INDEX
    Explanations

    weapons

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

    No Comments

    Negative Logits
    MED
    -18.88
     weapons
    -18.75
     Weapons
    -18.00
    Weapons
    -16.50
    武器
    -16.25
     magnet
    -16.13
    _api
    -16.00
     Magnet
    -15.88
    Med
    -15.75
    动
    -15.75
    POSITIVE LOGITS
    unistd
    21.25
    -UA
    19.13
    Earth
    17.75
     culture
    17.50
    mount
    17.50
     races
    17.13
    <ul
    16.88
     UR
    16.88
     race
    16.75
     π
    16.75
    Activations Density 0.265%

    No Known Activations