© 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. 65194
    Prev
    Next
    INDEX
    Explanations

    literal symbols and separators

    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
    ñez
    -0.07
    æĹĭ
    -0.07
    æ¯ıå½ĵ
    -0.07
    ׳×Ļת
    -0.07
    enho
    -0.07
    ontan
    -0.07
    'value
    -0.06
    endorf
    -0.06
    éné
    -0.06
    åľ¨åħ¶ä¸Ń
    -0.06
    POSITIVE LOGITS
    åĪĨéļĶ
    0.08
    æĸ°åŀĭåĨłçĬ¶çĹħæ¯ĴæĦŁæŁĵçļĦ
    0.06
    åĪĨåī²
    0.06
    æĸ°çļĦä¸Ģ
    0.06
    separator
    0.06
    mica
    0.06
    hart
    0.06
     Pett
    0.06
    ç»ıæµİ社ä¼ļåıijå±ķ
    0.06
    alone
    0.06
    Activations Density 0.048%

    No Known Activations