© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14438
    Prev
    Next
    INDEX
    Explanations

    [digit] => 2

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

    No Comments

    Negative Logits
    gency
    -18.13
    иона
    -15.63
    iens
    -13.81
    bidden
    -13.56
     sounding
    -13.31
    与时
    -13.25
    aign
    -13.06
    壤
    -12.75
    viously
    -12.69
    جب
    -12.69
    POSITIVE LOGITS
    �
    16.25
    orn
    15.31
    ysics
    15.00
    鲨
    15.00
    儒
    14.94
     xếp
    14.69
    ORN
    14.69
    .ol
    14.63
     Ratings
    14.38
    xdf
    14.19
    Activations Density 0.038%

    No Known Activations