© 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. 31424
    Prev
    Next
    INDEX
    Explanations

    universal concepts and systems

    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
    gia
    -0.08
    cia
    -0.08
    临éŨ
    -0.08
    .optional
    -0.07
    æľ¬åŃ£
    -0.07
    è¾ħ导
    -0.07
    ARDS
    -0.07
    جÙĬÙĨ
    -0.07
    ivs
    -0.07
    åĪĨå·¦åı³
    -0.07
    POSITIVE LOGITS
     univer
    0.08
    ç»Ŀ对çļĦ
    0.08
    æ°¸æģĴ
    0.08
    è¿IJåĬ¨çļĦ
    0.07
    æĻ®éģįçļĦ
    0.07
    å¢ĵ
    0.07
    ä¸ĢåĪ»
    0.07
     universal
    0.07
    åľ°çIJĥä¸Ĭ
    0.07
    ç»Ŀ对
    0.07
    Activations Density 0.001%

    No Known Activations