© 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. 14429
    Prev
    Next
    INDEX
    Explanations

    [title] => [surname]

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

    No Comments

    Negative Logits
    -spinner
    -16.00
    榖
    -15.75
    ott
    -15.06
     Utt
    -14.88
     Antonio
    -14.56
    洪
    -14.38
     bott
    -14.13
    安东尼
    -14.00
     Atlanta
    -13.88
    .ant
    -13.88
    POSITIVE LOGITS
    imas
    20.38
    pei
    19.63
    ALAR
    19.38
    ernen
    18.63
    raz
    17.75
    ele
    17.13
    (im
    17.13
     pierced
    16.63
    ieres
    16.00
    prestashop
    16.00
    Activations Density 0.581%

    No Known Activations