© 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. 15045
    Prev
    Next
    INDEX
    Explanations

    Sufi orders

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

    No Comments

    Negative Logits
    sun
    -18.38
    巴士
    -17.13
    高尔夫
    -16.75
    孚
    -16.75
    BASH
    -16.50
    "She
    -16.50
    象
    -16.13
    呦
    -15.94
    mars
    -15.94
    bearer
    -15.88
    POSITIVE LOGITS
    leton
    14.81
     retro
    13.56
    Copy
    13.25
    .defaultProps
    13.19
     Retro
    13.19
    onic
    13.19
    rop
    13.13
    เพชร
    12.69
     коллектив
    12.56
     Front
    12.50
    Activations Density 0.148%

    No Known Activations