© 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. 15465
    Prev
    Next
    INDEX
    Explanations

    say class

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

    No Comments

    Negative Logits
    unger
    -16.75
    uth
    -16.00
    .monitor
    -15.88
    蝇
    -15.50
    osaur
    -15.44
    恐龙
    -15.44
    htar
    -15.13
    .sax
    -15.13
    糖果
    -15.00
     Mona
    -14.88
    POSITIVE LOGITS
     class
    27.25
    阶级
    27.13
    班
    25.00
     Class
    24.63
     classes
    24.50
     classe
    24.25
     Classe
    23.75
    _class
    23.50
    Class
    23.00
    Classes
    22.88
    Activations Density 0.366%

    No Known Activations