© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1795
    Prev
    Next
    INDEX
    Explanations

    photosynthesis

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

    No Comments

    Negative Logits
     psychology
    -20.88
     Psychology
    -19.13
    psych
    -18.63
    atism
    -17.75
     Photoshop
    -17.13
    Psych
    -16.38
    看电视
    -16.38
    wheel
    -16.38
     Psychological
    -16.25
     astrology
    -16.00
    POSITIVE LOGITS
    数据库
    15.25
    (database
    15.13
     databases
    14.56
    罪
    14.13
    �
    14.00
    database
    13.75
     loan
    13.69
    离子
    13.63
     SqlCommand
    13.56
     database
    13.50
    Activations Density 0.058%

    No Known Activations