© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16270
    Prev
    Next
    INDEX
    Explanations

    [part] => [combined]

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

    No Comments

    Negative Logits
    白糖
    -20.13
    香蕉
    -19.75
    土豆
    -19.50
     pineapple
    -19.38
    胡萝卜
    -19.13
     Josef
    -18.88
     aluminium
    -18.75
    柑
    -18.75
    辣椒
    -18.63
     garlic
    -18.50
    POSITIVE LOGITS
    dge
    18.13
    流动
    18.13
    -flow
    17.88
    .Cross
    17.63
    纵横
    17.25
    adow
    16.75
    .Att
    16.75
    周转
    16.50
     Perc
    16.50
     Atlas
    16.50
    Activations Density 0.894%

    No Known Activations