© 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. 14939
    Prev
    Next
    INDEX
    Explanations

    configuration terms

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

    No Comments

    Negative Logits
    资料
    -16.88
    包
    -16.63
    公式
    -16.13
    布
    -15.31
    联
    -15.31
    工程
    -15.31
    访
    -15.06
    民
    -14.56
    肚
    -14.50
    连
    -14.44
    POSITIVE LOGITS
    Sym
    15.50
     underage
    15.44
    ->{$
    15.31
    yro
    15.13
    -lang
    14.75
    oldt
    14.75
    onis
    14.75
     *</
    14.69
    *</
    14.63
    rna
    14.50
    Activations Density 0.026%

    No Known Activations

    This feature has no known activations.