© 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. 10885
    Prev
    Next
    INDEX
    Explanations

    probability independence events

    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
    é¥
    -0.09
     expanded
    -0.08
    ä¸įåłª
    -0.08
    æĹ¥æ¸IJ
    -0.07
    æıIJåıĸ
    -0.07
    vale
    -0.07
     Cint
    -0.07
    loat
    -0.07
    ensiones
    -0.07
    éģ¿
    -0.07
    POSITIVE LOGITS
    çĭ¬ç«ĭ
    0.08
     independent
    0.07
    çĭ¬ç«ĭæĢ§
    0.07
    对åħ¶ä»ĸ
    0.07
     influenced
    0.07
    çĭ¬ç«ĭçļĦ
    0.07
    å¯¹æľªæĿ¥
    0.07
    epend
    0.07
     probabilities
    0.07
    äºĮ个
    0.07
    Activations Density 0.019%

    No Known Activations