© 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. 19833
    Prev
    Next
    INDEX
    Explanations

    maximum or limit

    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
    ä¼¼æĺ¯
    -0.08
    ä¾ĿçĦ¶åŃĺåľ¨
    -0.07
    ä¸ĵåĮº
    -0.07
    ä¸įåİĮ
    -0.07
    çĤ¹åĩ»ä¸ĭæĸ¹
    -0.07
    à¸Īà¸Ńม
    -0.07
    alp
    -0.07
     пÑĢоÑģ
    -0.07
    ledon
    -0.07
    DECL
    -0.07
    POSITIVE LOGITS
    /max
    0.10
    åĴĮæľĢ
    0.09
    /full
    0.09
    ä¹Łæĺ¯æľĢ
    0.08
     possible
    0.08
    -max
    0.08
     fullest
    0.08
    满
    0.08
     maxim
    0.08
     δÏħνα
    0.08
    Activations Density 0.055%

    No Known Activations