© 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. 11514
    Prev
    Next
    INDEX
    Explanations

    quantifiers and counts

    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
    erre
    -0.07
    abal
    -0.07
    bsp
    -0.07
    ä¸İç¾İåĽ½
    -0.07
    Ư
    -0.07
    æĥ³åĩº
    -0.07
    éĻĦä¸Ĭä¸Ģ
    -0.07
     daraus
    -0.06
    ç§ijæĬĢå±Ģ
    -0.06
    -footer
    -0.06
    POSITIVE LOGITS
     bern
    0.08
     copies
    0.07
    åIJĮ为
    0.07
    é¦ĸèµŀ
    0.07
     deteri
    0.07
    à°ªà±ģ
    0.07
    yo
    0.07
     ordinary
    0.07
    copies
    0.06
    æĬ¥çº¸
    0.06
    Activations Density 0.088%

    No Known Activations