© 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. 1434
    Prev
    Next
    INDEX
    Explanations

    say words after optical

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

    No Comments

    Negative Logits
    光
    -33.25
    光学
    -32.75
     optical
    -32.50
     Optical
    -30.88
    光线
    -26.88
    氧气
    -26.63
    光照
    -24.75
    光电
    -24.50
     oxygen
    -24.00
     Oxygen
    -23.13
    POSITIVE LOGITS
    炭
    18.00
     carbon
    17.13
     Carbon
    17.13
    carbon
    16.63
    碳
    16.38
    /MM
    16.25
    Carbon
    16.13
     menus
    14.44
     menu
    13.19
    menu
    12.94
    Activations Density 0.022%

    No Known Activations