© 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. 16660
    Prev
    Next
    INDEX
    Explanations

    certain + quantifier

    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
    erii
    -0.10
    ï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭ
    -0.09
    er
    -0.09
    etine
    -0.09
    å¿ĥçľ¼
    -0.09
    ////////////////////////////////////////////////////////////////////////////
    -0.09
    äºĭåįĬåĬŁåĢį
    -0.09
    ////////////////////////////////////////////////////////////
    -0.09
    quel
    -0.09
    sor
    -0.09
    POSITIVE LOGITS
    ç¨ĭ度çļĦ
    0.09
    æŶéĹ´åĨħ
    0.08
    aining
    0.08
    iation
    0.07
    maÃŁen
    0.07
    erness
    0.07
     обÑĢазом
    0.07
    éĻIJ度çļĦ
    0.07
    ç¨ĭ度ä¸Ĭ
    0.07
    gnore
    0.07
    Activations Density 0.005%

    No Known Activations