© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1112
    Prev
    Next
    INDEX
    Explanations

    articles

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

    No Comments

    Negative Logits
     articles
    -39.25
    文章
    -38.75
     article
    -38.50
     ARTICLE
    -37.00
    articles
    -36.75
    <Article
    -36.00
     Article
    -35.75
     Articles
    -35.25
    -article
    -35.25
    _article
    -34.75
    POSITIVE LOGITS
    ос
    16.88
    amma
    16.00
     Dynamo
    15.94
    迪
    15.63
     Dynam
    15.13
    _SOUND
    14.56
    锰
    14.50
    辽宁省
    14.44
    电池
    14.00
     Poison
    13.88
    Activations Density 0.109%

    No Known Activations