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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16244
    Prev
    Next
    INDEX
    Explanations

    ends with 上

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

    No Comments

    Negative Logits
    bsites
    -17.63
     entrances
    -15.31
     Gmail
    -15.06
    itura
    -14.38
     internet
    -14.00
    (library
    -14.00
     gmail
    -13.88
     Shapiro
    -13.81
    .Lib
    -13.81
     ado
    -13.69
    POSITIVE LOGITS
    設
    18.00
    流淌
    17.25
     pack
    16.75
    设有
    16.75
     packing
    16.75
     Packing
    16.63
    setIcon
    16.25
    设
    16.13
    设置
    16.00
    émon
    15.88
    Activations Density 0.212%

    No Known Activations