© 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. 29079
    Prev
    Next
    INDEX
    Explanations

    px, pt, em, px, em

    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
    icable
    -0.07
     nor
    -0.07
    -0.06
    åIJīæĸ¯
    -0.06
    enson
    -0.06
    itzt
    -0.06
    顾éĹ®
    -0.06
    theit
    -0.06
    æĸĮ
    -0.06
    å¼ĤæĢ§
    -0.06
    POSITIVE LOGITS
    itten
    0.07
    isen
    0.07
    çĿĢä¸ĢèĤ¡
    0.06
    ç²¾æĺİ
    0.06
    اÙĨÙĪ
    0.06
    oton
    0.06
    zec
    0.06
    alion
    0.06
    etten
    0.06
    å¼Ģè¡Į
    0.06
    Activations Density 0.001%

    No Known Activations