© 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. 11464
    Prev
    Next
    INDEX
    Explanations

    lists of items following a separator

    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
    ož
    -0.06
    (or
    -0.06
    .mail
    -0.06
    ä¹ĭéģĵ
    -0.06
    æľįåĬ¡å·¥ä½ľ
    -0.06
    ĥĿ
    -0.06
    utsch
    -0.06
    æĪĸ以ä¸Ĭ
    -0.06
    plit
    -0.06
    edia
    -0.06
    POSITIVE LOGITS
     etc
    0.14
    以åıĬ对
    0.12
    以åıĬ
    0.11
     usw
    0.11
    ,and
    0.11
     ฯลฯ
    0.11
    ãģĿãģĹãģ¦
    0.11
    è¿ĺæľīå°±æĺ¯
    0.10
    ãģ¨ãģĦãģ£ãģŁ
    0.10
     ê·¸ë¦¬ê³ł
    0.10
    Activations Density 0.055%

    No Known Activations