© 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. 14746
    Prev
    Next
    INDEX
    Explanations

    numeric ranges

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

    No Comments

    Negative Logits
    MARY
    -17.50
     dumps
    -17.25
    iona
    -17.25
    玩游戏
    -17.00
    _mx
    -17.00
    Sugar
    -16.63
    TabPage
    -16.38
    蹑
    -16.38
    你怎么
    -16.13
    umps
    -15.94
    POSITIVE LOGITS
    ′
    13.56
    IOUS
    11.88
     norm
    11.69
     outer
    11.63
    rescia
    11.44
    norm
    11.38
     Normalize
    11.31
    ’
    11.25
    .outer
    10.94
     normalize
    10.81
    Activations Density 0.014%

    No Known Activations