© 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. 1633
    Prev
    Next
    INDEX
    Explanations

    say "al" words

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

    No Comments

    Negative Logits
    游泳
    -18.00
     swim
    -16.50
     swimming
    -16.00
    谌
    -15.69
     artificial
    -15.69
    меди
    -15.56
     Artificial
    -15.38
     swims
    -15.25
     Med
    -15.00
     Medi
    -14.19
    POSITIVE LOGITS
    アル
    42.75
    Al
    37.75
    -al
    35.00
     al
    34.00
    阿尔
    34.00
     Al
    33.75
    算法
    33.50
    (al
    33.25
    'al
    33.00
     algebra
    32.75
    Activations Density 0.413%

    No Known Activations