© 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. 1811
    Prev
    Next
    INDEX
    Explanations

    port city

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

    No Comments

    Negative Logits
    ’acc
    -16.13
     light
    -15.94
    玻璃
    -15.44
    Alexander
    -15.31
     accel
    -15.19
     equation
    -15.00
    둥
    -14.94
     engineered
    -14.88
     Marco
    -14.81
    迢
    -14.81
    POSITIVE LOGITS
    画
    16.88
    fish
    16.13
    itical
    16.00
    evin
    15.75
    棋
    15.19
    矢
    15.00
    ünst
    15.00
    cart
    14.19
     Saul
    14.19
     fish
    13.75
    Activations Density 0.264%

    No Known Activations