© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7579
    Prev
    Next
    INDEX
    Explanations

    also added

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lightbox
    -0.07
    lobber
    -0.07
    isata
    -0.06
    elok
    -0.06
    rosse
    -0.06
    çİĭæĢĿ
    -0.06
    å¾Īæľī
    -0.06
    reater
    -0.06
    æµ·é»ĺ
    -0.06
    åĴĮ大
    -0.06
    POSITIVE LOGITS
    ster
    0.07
    ums
    0.07
    utzer
    0.07
    çĶ¨éĩı
    0.07
    ä¹ŁæĽ´
    0.07
    ä¹Łä¸įæķ¢
    0.07
    asu
    0.06
    leti
    0.06
    akin
    0.06
    sters
    0.06
    Activations Density 0.009%

    No Known Activations