© 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. 1150
    Prev
    Next
    INDEX
    Explanations

    [basketball] => [basketball]

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

    No Comments

    Negative Logits
    canvas
    -21.25
    .canvas
    -20.25
     canvas
    -19.75
     NASA
    -18.50
    水墨
    -18.38
    	canvas
    -17.88
    医保
    -17.75
     Basketball
    -17.25
    墨
    -17.13
     basketball
    -16.75
    POSITIVE LOGITS
     Equip
    19.00
    Equip
    18.75
    Salt
    17.63
    Û
    17.63
     SAL
    17.38
     salt
    17.25
     salts
    16.75
    equipment
    16.38
    iap
    16.38
     Schwe
    16.00
    Activations Density 0.238%

    No Known Activations