© 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. 15192
    Prev
    Next
    INDEX
    Explanations

    month names

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

    No Comments

    Negative Logits
    鼠
    -16.50
    骝
    -16.38
    伊拉
    -16.13
    idal
    -15.88
    弹
    -15.13
    MDB
    -15.00
    istan
    -14.63
    钪
    -14.50
    bles
    -14.31
    燃
    -14.19
    POSITIVE LOGITS
     dime
    20.00
     Hatch
    19.00
     Vick
    17.75
     Victoria
    17.38
    梨
    17.25
     Vince
    17.13
    ouch
    16.88
     печ
    16.75
     Vik
    16.50
     Jacket
    16.25
    Activations Density 0.072%

    No Known Activations