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

    Neuronpedia

    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. 15770
    Prev
    Next
    INDEX
    Explanations

    smartphone

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

    No Comments

    Negative Logits
    ivec
    -17.50
    centroid
    -17.38
    automation
    -17.00
    Ball
    -17.00
    ุม
    -16.75
    LogFile
    -16.63
    风湿
    -16.63
    .Euler
    -16.50
    CTest
    -16.50
     disg
    -16.38
    POSITIVE LOGITS
    手机
    39.25
     mobile
    35.00
     phone
    34.25
     smartphone
    33.75
    -phone
    33.25
     phones
    33.00
     Mobile
    32.50
    智能手机
    32.50
     smartphones
    32.25
     Smartphone
    32.25
    Activations Density 0.480%

    No Known Activations