© 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. 42500
    Prev
    Next
    INDEX
    Explanations

    variables followed by specific punctuation or delimiters

    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
    'C
    -0.07
    tega
    -0.06
    ermann
    -0.06
    أس
    -0.06
    çĦ¶æĺ¯
    -0.06
    éĻĮçĶŁäºº
    -0.06
    ãĥµ
    -0.06
    æĴ¼
    -0.06
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    -0.06
    \\"
    -0.06
    POSITIVE LOGITS
    çļĦ人æĿ¥è¯´
    0.10
    人æĿ¥è¯´
    0.10
     ÙģØ¥ÙĨÙĩ
    0.09
    æĿ¥è¯´
    0.09
    èĢĮè¨Ģ
    0.08
    _except
    0.08
     ÙĩÙĨاÙĥ
    0.08
     there
    0.07
     _______,
    0.07
    __,
    0.07
    Activations Density 0.011%

    No Known Activations