© 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. 15115
    Prev
    Next
    INDEX
    Explanations

    say times

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

    No Comments

    Negative Logits
    istine
    -17.63
    ronics
    -17.38
    sein
    -16.75
    골
    -16.50
     FormControl
    -16.50
    очка
    -16.50
    emodel
    -15.81
    FormItem
    -15.69
    gó
    -15.63
    icot
    -15.56
    POSITIVE LOGITS
    legg
    14.25
    olis
    13.81
     cabe
    13.50
     süre
    12.94
     дня
    12.00
    обы
    11.81
    中午
    11.81
     Scarborough
    11.75
    tek
    11.13
    到来
    11.13
    Activations Density 0.034%

    No Known Activations