© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16031
    Prev
    Next
    INDEX
    Explanations

    head

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

    No Comments

    Negative Logits
     menus
    -17.50
    orro
    -16.00
    bre
    -16.00
    訓練
    -15.81
    indy
    -15.69
    雷锋
    -15.38
    ddb
    -15.31
     intf
    -15.25
     IID
    -15.25
    MENU
    -15.25
    POSITIVE LOGITS
    unga
    18.63
    unts
    15.56
    髅
    15.13
    _ATTACH
    15.00
     Cannon
    14.81
     Nun
    14.69
    顶
    14.69
    洽
    14.63
    hl
    14.31
     cabel
    14.19
    Activations Density 0.041%

    No Known Activations