© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14837
    Prev
    Next
    INDEX
    Explanations

    potatoes

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

    No Comments

    Negative Logits
    .semantic
    -16.88
    LEAN
    -16.13
    ære
    -15.50
    瀑布
    -15.38
    漏水
    -15.19
    :frame
    -14.94
    沆
    -14.88
    otionEvent
    -14.56
    嵩
    -14.56
    师范
    -14.44
    POSITIVE LOGITS
    土豆
    27.38
    薯
    21.25
     potato
    20.75
     potatoes
    20.75
     Potato
    19.88
    HashTable
    18.88
    红薯
    18.25
    🥔
    17.25
    变身
    17.13
    _hash
    16.13
    Activations Density 0.101%

    No Known Activations