© 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. 13971
    Prev
    Next
    INDEX
    Explanations

    say legal terms

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

    No Comments

    Negative Logits
    开盘
    -19.63
    _analysis
    -19.63
    analysis
    -18.88
    分析
    -18.25
    ako
    -17.25
     Pixel
    -17.13
     analyzing
    -17.00
    .desktop
    -17.00
     analyzed
    -17.00
     analysis
    -17.00
    POSITIVE LOGITS
    布置
    16.75
    sey
    15.31
     order
    15.25
    Acts
    15.25
     orders
    15.19
     Acts
    15.06
     Act
    14.88
    .setItems
    14.81
     law
    14.63
     act
    14.56
    Activations Density 0.238%

    No Known Activations