© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1053
    Prev
    Next
    INDEX
    Explanations

    burning

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

    No Comments

    Negative Logits
     burns
    -47.75
     burn
    -46.75
     Burn
    -45.50
     burning
    -45.00
    Burn
    -44.00
     burned
    -43.75
    烧
    -40.75
    burn
    -39.50
     Burning
    -38.75
    燒
    -38.25
    POSITIVE LOGITS
     Jes
    16.25
     Cf
    15.81
    efa
    14.56
     CIF
    14.56
    word
    14.56
    df
    14.38
    CID
    14.31
    sf
    13.94
    咖啡
    13.75
    CF
    13.69
    Activations Density 0.103%

    No Known Activations