© 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. 14922
    Prev
    Next
    INDEX
    Explanations

    author names

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

    No Comments

    Negative Logits
    ''.
    -16.13
    .".
    -14.94
    '.
    -14.81
    '\
    -14.06
    '-
    -13.88
    {}.
    -13.81
    '|
    -13.69
    =".
    -13.69
    [];
↵
    -13.44
    '{
    -13.38
    POSITIVE LOGITS
    riz
    16.63
    东方
    16.25
    bih
    15.75
    喷
    15.25
    建国
    15.19
    叠
    15.19
    中铁
    15.13
    Assignment
    14.88
     Wing
    14.75
    结构
    14.75
    Activations Density 0.088%

    No Known Activations