© 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. 14593
    Prev
    Next
    INDEX
    Explanations

    say Chinese characters

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

    No Comments

    Negative Logits
    b
    -44.50
    B
    -42.50
    _b
    -42.25
    -b
    -40.00
     B
    -38.75
     b
    -38.50
    .b
    -38.25
    $b
    -38.25
    ｂ
    -37.75
    *b
    -36.25
    POSITIVE LOGITS
    IDGET
    16.13
    阊
    14.19
    guards
    13.25
    莨
    13.06
    side
    12.81
    Guard
    12.38
     Affero
    12.25
    ritten
    12.25
    饴
    11.94
     rall
    11.81
    Activations Density 1.186%

    No Known Activations