© 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. 1578
    Prev
    Next
    INDEX
    Explanations

    say "CSS"

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

    No Comments

    Negative Logits
    博物馆
    -40.25
     museum
    -38.25
     museums
    -38.00
     Museum
    -35.00
     Muse
    -30.63
     Mus
    -27.25
     mus
    -26.38
     Musk
    -24.63
     µ
    -24.63
    Mus
    -24.25
    POSITIVE LOGITS
    CSS
    18.13
    css
    18.13
     CSS
    17.88
     IHttp
    17.75
     css
    17.50
     Dynamic
    17.50
    Css
    17.50
    iani
    17.50
    .getItems
    17.25
    _css
    16.00
    Activations Density 0.069%

    No Known Activations