© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25170
    Prev
    Next
    INDEX
    Explanations

    reading input streams and classes

    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
    æĻĴ
    -0.07
    lash
    -0.07
     Lesb
    -0.07
    celli
    -0.07
     Stéph
    -0.07
    RELATED
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    pla
    -0.06
    ãĤ¯ãĥ©ãĤ¤
    -0.06
    èIJ¤çģ«
    -0.06
    POSITIVE LOGITS
    åłªæ¯Ķ
    0.08
    ä¸Ń大
    0.08
    æ¸Ĭ
    0.08
    strings
    0.07
    à¹īว
    0.07
    apes
    0.07
    æĸ¹æ³ķè¿Ľè¡Į
    0.07
    дÑĸй
    0.07
    enges
    0.07
    noj
    0.07
    Activations Density 0.021%

    No Known Activations