© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14068
    Prev
    Next
    INDEX
    Explanations

    say contact

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

    No Comments

    Negative Logits
    lya
    -17.25
    冶金
    -16.13
    腓
    -15.75
    PixelFormat
    -15.50
    踢
    -15.00
    composition
    -15.00
    匹配
    -14.69
    发展战略
    -14.56
     Viking
    -14.56
    Reducer
    -14.56
    POSITIVE LOGITS
     contacto
    22.25
    接触到
    22.00
     contact
    22.00
    接触
    21.25
    传染
    21.13
     transfer
    20.88
    trans
    20.63
    -trans
    20.50
    contact
    20.13
     Contact
    20.00
    Activations Density 0.503%

    No Known Activations