© 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. 1179
    Prev
    Next
    INDEX
    Explanations

    脉弦细

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

    No Comments

    Negative Logits
     farmers
    -15.44
    茶叶
    -14.81
    uct
    -14.50
    fabs
    -14.50
    今生
    -14.44
    itten
    -14.25
     Ark
    -14.06
    apol
    -13.88
    arm
    -13.88
    farm
    -13.81
    POSITIVE LOGITS
     Wort
    19.75
    Magic
    19.38
    美
    19.25
    货币
    19.13
     magic
    18.88
    马
    18.75
     Magic
    18.50
     magical
    18.38
     getCode
    18.25
    MAP
    17.75
    Activations Density 0.396%

    No Known Activations