© 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. 34204
    Prev
    Next
    INDEX
    Explanations

    walking through code

    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
    æݸ
    -0.07
    ائ
    -0.07
    ège
    -0.07
    pas
    -0.07
     Wheeler
    -0.07
    ç«ĭçļĦ
    -0.07
    ibrary
    -0.07
    ynie
    -0.07
    éli
    -0.07
    stime
    -0.07
    POSITIVE LOGITS
    æĺ¯å¦Ĥä½ķ
    0.07
    _running
    0.06
    plash
    0.06
    mai
    0.06
    running
    0.06
    ä¸į详
    0.06
     refere
    0.06
    anaf
    0.06
    uss
    0.06
    èµ°åIJİ
    0.06
    Activations Density 0.001%

    No Known Activations