© 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. 65513
    Prev
    Next
    INDEX
    Explanations

    return, repeat, recurrence

    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
    ç»ĪæĹ¥
    -0.08
    åįĬæĻĮ
    -0.08
     سا
    -0.07
    rame
    -0.07
    ÙĪائ
    -0.07
    èĦ±é¢ĸèĢĮåĩº
    -0.07
    _INITIALIZ
    -0.07
    AttributeName
    -0.07
    ragon
    -0.07
    åħ¥å¾®
    -0.07
    POSITIVE LOGITS
     repeat
    0.17
    éĩįå¤į
    0.16
     repeats
    0.15
     repetition
    0.15
    repeat
    0.15
    ä¸ĭä¸Ģ次
    0.14
     repeated
    0.14
    Repeat
    0.14
     Repeat
    0.14
     повÑĤоÑĢ
    0.13
    Activations Density 0.375%

    No Known Activations