© 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. 1719
    Prev
    Next
    INDEX
    Explanations

    do not say API

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

    No Comments

    Negative Logits
    API
    -56.75
     API
    -55.75
     api
    -55.50
     APIs
    -53.00
    api
    -51.25
    -api
    -49.50
    	api
    -49.25
    _api
    -48.75
    Api
    -48.25
    -API
    -48.00
    POSITIVE LOGITS
     Martian
    15.06
    football
    14.63
    Football
    14.31
    rans
    14.25
     Mars
    14.13
     Karn
    13.13
    _DRAW
    12.81
     Hud
    12.75
     football
    12.63
    火星
    12.56
    Activations Density 0.057%

    No Known Activations