© 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. 22355
    Prev
    Next
    INDEX
    Explanations

    repetition of words or ideas

    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
    erland
    -0.09
     индивидÑĥалÑĮно
    -0.08
    ×ķ×ĸ
    -0.08
    ķĮ
    -0.08
    urat
    -0.07
     ára
    -0.07
    æ´ªæµģ
    -0.07
    оне
    -0.07
    /bind
    -0.07
    anken
    -0.07
    POSITIVE LOGITS
    åīį两
    0.08
     Ngá»įc
    0.07
    ilas
    0.06
    èıĬ
    0.06
    åīįä¸Ģ
    0.06
    اضÙĬ
    0.06
     strong
    0.06
    اÙģÙĬØ©
    0.06
    çľģåĬĽ
    0.06
    éĿ¢è¯ķæŶéĹ´
    0.06
    Activations Density 0.002%

    No Known Activations