© 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. 1518
    Prev
    Next
    INDEX
    Explanations

    code prefixes and punctuation

    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
    apes
    -0.08
    ä¸ĢæĿ¡é¾Ļ
    -0.08
    urato
    -0.08
    heber
    -0.08
    stalk
    -0.08
    è¯ģæį®è¯ģæĺİ
    -0.08
    æ¯ıéĢ±
    -0.07
    ئاب
    -0.07
    tora
    -0.07
    viewer
    -0.07
    POSITIVE LOGITS
    æīĵå¼Ģ
    0.07
    è°ĥçĶ¨
    0.06
    æij¸
    0.06
    eg
    0.06
    å¼Ģåľº
    0.06
    æ£ĢæŁ¥
    0.06
    åĪĿå§ĭåĮĸ
    0.06
    éģ½
    0.06
     Initialization
    0.06
    ism
    0.06
    Activations Density 0.005%

    No Known Activations