© 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. 24371
    Prev
    Next
    INDEX
    Explanations

    "Courtney" surname

    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
    ou
    -0.07
    awa
    -0.07
    ellini
    -0.07
    enga
    -0.07
    .googleapis
    -0.07
    acci
    -0.07
    åı¯æĥ³èĢĮçŁ¥
    -0.07
    mara
    -0.07
    å¾Įãģ¯
    -0.07
    ousand
    -0.07
    POSITIVE LOGITS
    èIJ½å¯ŀ
    0.07
    zÃŃ
    0.07
     verst
    0.06
    ä¸İåĽ½åĨħ
    0.06
    ä¿¡çļĦ
    0.06
    inian
    0.06
    tuk
    0.06
    ãģ£ãģıãĤĬ
    0.06
    éĹ»
    0.06
    æŃ¢
    0.06
    Activations Density 0.002%

    No Known Activations