© 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. 15204
    Prev
    Next
    INDEX
    Explanations

    say "symbol"

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

    No Comments

    Negative Logits
    ifications
    -15.50
    äre
    -14.94
    GetInstance
    -14.75
    麽
    -14.00
     yên
    -13.81
    alité
    -13.38
    蒟
    -13.25
    -ins
    -13.25
    ellig
    -13.13
    GetObject
    -12.88
    POSITIVE LOGITS
    输出
    20.50
    符号
    18.63
    组织
    18.38
    编码
    17.63
    emit
    17.00
     输出
    16.88
    领导
    16.88
    聘请
    16.75
    舉
    16.38
    (symbol
    16.25
    Activations Density 0.284%

    No Known Activations