© 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. 25998
    Prev
    Next
    INDEX
    Explanations

    documentationcenter:

    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
    å¯ħ
    -0.07
    ç«ĭ交
    -0.07
    engin
    -0.07
    ônimo
    -0.07
    \n
    -0.06
    ÙĪÙĦا
    -0.06
    amerate
    -0.06
    èį£åįİ
    -0.06
    éĿ©
    -0.06
    olph
    -0.06
    POSITIVE LOGITS
    룡
    0.08
    rike
    0.08
    ä¸Ģç±»
    0.07
    yesi
    0.07
    æĦıè§ģåıįé¦Ī
    0.07
    æĬĬæĪij们
    0.07
    illery
    0.07
    ä¹ŁæĬĬ
    0.07
    ä¸ĢåĪĻ
    0.07
    ŀ
    0.07
    Activations Density 0.002%

    No Known Activations