© 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. 13334
    Prev
    Next
    INDEX
    Explanations

    performances, fulfillment, 0-year-old

    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
    ander
    -0.07
    ç¢
    -0.07
    è¿Ļæł·çļĦè¯Ŀ
    -0.06
    appy
    -0.06
    _cv
    -0.06
    ikit
    -0.06
    缸åħ³æĸĩç«ł
    -0.06
     Rodrig
    -0.06
    _vp
    -0.06
    utz
    -0.06
    POSITIVE LOGITS
    ä¸Ķä¸į
    0.09
    éĢīæĭ©ä¸į
    0.08
    lar
    0.08
    èĻ½æľī
    0.08
    èĻ½çĦ¶æľī
    0.07
    boli
    0.07
    ä¸Ķ
    0.07
    plib
    0.07
    ä¸įä¼ij
    0.07
    åľ¨æ²¡æľī
    0.07
    Activations Density 0.208%

    No Known Activations