© 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. 1629
    Prev
    Next
    INDEX
    Explanations

    [encoding] => [encoding]

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

    No Comments

    Negative Logits
    Encoding
    -26.13
    ENG
    -23.63
     encode
    -23.00
     encoding
    -22.13
    encoding
    -21.88
    Encode
    -21.88
    (Encoding
    -21.88
    _encoding
    -21.50
    _ENCODING
    -21.13
     Eng
    -21.00
    POSITIVE LOGITS
    lambda
    17.00
    .lambda
    16.38
     business
    15.81
     JavaScript
    15.31
    的学生
    15.25
     lambda
    15.19
    .Business
    14.94
     Business
    14.81
     SHOP
    14.75
    _business
    14.38
    Activations Density 0.075%

    No Known Activations