© 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. 2606
    Prev
    Next
    INDEX
    Explanations

    probability density, measure

    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
    oola
    -0.07
    itor
    -0.07
    íijľ
    -0.07
    ä¸ĢæľĿ
    -0.07
    解æ¯Ĵ
    -0.07
    obo
    -0.07
    обÑĢа
    -0.07
     proved
    -0.06
    обо
    -0.06
    æľĢä½İä»·
    -0.06
    POSITIVE LOGITS
     Probability
    0.08
    Probability
    0.08
     probability
    0.08
    PTY
    0.08
    probability
    0.07
    åħ¨å¤©
    0.07
    èĸĦ
    0.07
     dud
    0.07
    é¢ĸ
    0.07
    é£İå°ĺ
    0.07
    Activations Density 0.001%

    No Known Activations