© 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. 15299
    Prev
    Next
    INDEX
    Explanations

    => frac

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

    No Comments

    Negative Logits
     Garland
    -19.88
    orias
    -17.38
     UNIX
    -17.25
    PRS
    -16.88
     Everest
    -16.75
     Aspen
    -16.63
    斯顿
    -16.13
     Airbus
    -15.81
     BSD
    -15.63
     trần
    -15.56
    POSITIVE LOGITS
    abo
    16.38
    ago
    15.63
    ici
    14.00
    ku
    13.88
    ente
    13.75
     negro
    13.69
    y
    13.44
    Ali
    13.44
    寒假
    13.38
    shal
    13.31
    Activations Density 0.004%

    No Known Activations