© 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. 15347
    Prev
    Next
    INDEX
    Explanations

    [wife] => [name]

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

    No Comments

    Negative Logits
    食物
    -18.25
    组装
    -17.25
    =form
    -16.50
    闻
    -16.25
     form
    -16.25
    嗅
    -16.00
    形式
    -15.94
    abox
    -15.94
     Form
    -15.88
    報告
    -15.75
    POSITIVE LOGITS
     Lucia
    15.38
    _MED
    14.44
     Tina
    14.38
     ElementType
    14.25
    	TokenName
    14.13
    clair
    13.88
     divorced
    13.81
     Vanessa
    13.56
    .Arg
    13.50
    isel
    13.38
    Activations Density 0.104%

    No Known Activations