© 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. 16167
    Prev
    Next
    INDEX
    Explanations

    consecutive occurrences

    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
    éķ¿å¹´
    -0.07
    ontos
    -0.07
    warts
    -0.07
    inks
    -0.07
    ä»İå°ıå°±
    -0.07
    ä¹Ŀå·ŀ
    -0.06
    ÙĦÙĬÙĩ
    -0.06
    rij
    -0.06
    è¿Ī
    -0.06
    ä¸Ģä¸Ŀ
    -0.06
    POSITIVE LOGITS
     подÑĢÑıд
    0.15
     consecutive
    0.14
     consec
    0.13
     successive
    0.12
    缸继
    0.12
    à¸Ķà¹īวยà¸ģัà¸Ļ
    0.11
    ä¾Ŀ次
    0.11
     seguid
    0.10
     sequentially
    0.10
    æİ¥è¿ŀ
    0.10
    Activations Density 0.256%

    No Known Activations