© 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. 15118
    Prev
    Next
    INDEX
    Explanations

    number after parenthesis

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

    No Comments

    Negative Logits
    4
    -50.25
     four
    -46.50
     fourth
    -45.75
    四是
    -43.75
     Fourth
    -42.75
     Four
    -42.00
    ４
    -41.25
    four
    -40.75
     fours
    -40.00
    -four
    -39.75
    POSITIVE LOGITS
     Gust
    14.94
    deb
    13.06
    OCK
    12.75
    ijkstra
    12.25
     مباشر
    12.06
    utow
    11.88
    ingly
    11.75
    اذ
    11.63
    median
    11.56
    穰
    11.44
    Activations Density 1.111%

    No Known Activations