© 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. 34636
    Prev
    Next
    INDEX
    Explanations

    make or choose a decision

    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
    æ¿
    -0.08
    ÙİÙĬÙĴ
    -0.08
    æīĢæĢĿ
    -0.08
    èŀº
    -0.08
    ä½łæķ¢
    -0.07
    æİĮæı¡å¥½
    -0.07
    åıĮéĿ¢
    -0.07
    æĥ³æĸ¹
    -0.07
    ç¦ģåĮº
    -0.07
    ugas
    -0.07
    POSITIVE LOGITS
    éĢīåĩº
    0.18
     selection
    0.17
    æĭ©ä¼ĺ
    0.17
     selecting
    0.17
     Auswahl
    0.15
    selection
    0.15
    Selection
    0.15
     Selection
    0.15
     selects
    0.15
     selections
    0.14
    Activations Density 0.295%

    No Known Activations