© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15222
    Prev
    Next
    INDEX
    Explanations

    uncommon tokens

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

    No Comments

    Negative Logits
    这种情况
    -16.25
    ϕ
    -15.44
    西红柿
    -15.31
     Largest
    -14.38
    和个人
    -13.88
    ìm
    -13.56
    ${
    -13.56
    的颜色
    -13.50
    рей
    -13.50
     (�
    -13.25
    POSITIVE LOGITS
    掣
    17.88
     Cust
    17.75
    aupt
    17.00
    霆
    16.75
    牝
    16.63
    钊
    16.25
    ampion
    16.13
    旖
    15.81
    峥
    15.81
    obox
    15.75
    Activations Density 0.235%

    No Known Activations