© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11774
    Prev
    Next
    INDEX
    Explanations

    lasting, reliable, meaningful

    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
    arren
    -0.08
    akis
    -0.07
    åħ¸åŀĭçļĦ
    -0.07
    elj
    -0.07
    å¾Īå°ıçļĦ
    -0.07
    æĮĸæİĺåħ¬åı¸
    -0.07
     incompat
    -0.07
    巨大çļĦ
    -0.07
    à§ĩষ
    -0.07
    æŀģé«ĺçļĦ
    -0.07
    POSITIVE LOGITS
    æĿ¡çIJĨ
    0.09
     lasting
    0.08
    -rounded
    0.08
    -efficient
    0.08
    åĪ°æľī
    0.08
    óc
    0.08
     reliable
    0.08
    ä»·æł¼åIJĪçIJĨ
    0.08
     meaningful
    0.07
    å®īåħ¨åĴĮ
    0.07
    Activations Density 0.184%

    No Known Activations