© 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. 62632
    Prev
    Next
    INDEX
    Explanations

    preventive measures

    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
    exus
    -0.08
    OrCreate
    -0.08
    testdata
    -0.07
    asmine
    -0.07
    thro
    -0.07
    æ²ĥæĸ¯
    -0.07
    צ×Ļ
    -0.07
    oose
    -0.07
    Ùĩد
    -0.07
    egration
    -0.07
    POSITIVE LOGITS
    æݪæĸ½çļĦ
    0.10
    ä¸įåĬĽ
    0.09
    æľīæķĪæݪæĸ½
    0.09
    æݪæĸ½
    0.08
    å¾ĹåĬĽ
    0.08
    è¡ĮåĬ¨çļĦ
    0.08
    ioned
    0.08
     drastic
    0.08
    dden
    0.07
    colar
    0.07
    Activations Density 0.026%

    No Known Activations