© 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. 14873
    Prev
    Next
    INDEX
    Explanations

    section headings

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

    No Comments

    Negative Logits
    antas
    -19.50
    urent
    -19.00
    osph
    -17.25
    iot
    -17.13
    elves
    -17.13
    ilk
    -17.00
    ester
    -16.50
    iaz
    -16.38
    ius
    -16.25
    (screen
    -16.25
    POSITIVE LOGITS
    理由
    14.25
     Classified
    14.13
    YPE
    13.94
    egin
    13.19
    ANDING
    13.13
     Towards
    13.00
    สา
    13.00
    OT
    12.25
    事
    12.13
     Lever
    12.13
    Activations Density 0.200%

    No Known Activations