© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1275
    Prev
    Next
    INDEX
    Explanations

    alkaline soils

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

    No Comments

    Negative Logits
     makeStyles
    -18.13
    books
    -17.25
     Pdf
    -16.50
     Sacred
    -16.38
     sacred
    -16.00
     Adobe
    -15.81
     Dairy
    -15.81
     breast
    -15.81
    book
    -15.69
    PDF
    -15.69
    POSITIVE LOGITS
    伊朗
    20.13
    枪
    20.00
     guns
    19.00
    兵
    18.13
    sentence
    17.38
    璘
    17.38
    -lang
    17.25
     Iran
    17.25
     gunman
    17.13
    -gun
    17.13
    Activations Density 0.376%

    No Known Activations