© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14886
    Prev
    Next
    INDEX
    Explanations

    say acronyms

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

    No Comments

    Negative Logits
    ripe
    -17.00
    lime
    -15.00
    arez
    -14.19
    妃
    -13.69
    are
    -13.63
    贱
    -13.38
     Americans
    -13.13
    嘌
    -13.00
    厌
    -13.00
    rique
    -13.00
    POSITIVE LOGITS
    .cg
    19.25
    ng
    18.75
    tg
    18.38
    vg
    17.88
    Gab
    17.75
    葛
    17.63
    IDL
    17.50
    cg
    17.25
    spir
    17.00
    IG
    16.75
    Activations Density 0.010%

    No Known Activations