© 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. 33896
    Prev
    Next
    INDEX
    Explanations

    consecutive streak

    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
    chner
    -0.08
    带åĽŀ
    -0.08
    æ³Ľ
    -0.07
     Tiong
    -0.07
    iman
    -0.07
    æĮīæŶå®ĮæĪIJ
    -0.07
    iesa
    -0.07
    é¡
    -0.07
    iaux
    -0.07
     Late
    -0.07
    POSITIVE LOGITS
    è¿ŀç»Ń
    0.18
    è¿ŀç»ŃçļĦ
    0.16
     uninterrupted
    0.15
     consecutive
    0.15
    éĢ£çºĮ
    0.15
     contiguous
    0.14
     continuous
    0.13
    éĢ£ç¶ļ
    0.13
    å·²ç»ıè¿ŀç»Ń
    0.12
     ìĹ°ìĨį
    0.12
    Activations Density 0.069%

    No Known Activations