© 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. 51795
    Prev
    Next
    INDEX
    Explanations

    structured and ordered 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
    éĿĪæ´»
    -0.07
    羣è¯ļçļĦ
    -0.07
    çģµæ´»çļĦ
    -0.07
    æľįåĬ¡èĥ½åĬĽ
    -0.07
    èĩªçĦ¶äºº
    -0.07
     richest
    -0.07
    éľ²å¤©
    -0.07
     unprotected
    -0.07
    onga
    -0.06
     vra
    -0.06
    POSITIVE LOGITS
    严谨
    0.15
     rigid
    0.15
    æłĩåĩĨåĮĸ
    0.15
     structured
    0.14
    ç»ĵæŀĦåĮĸ
    0.14
    æľīæĿ¡ä¸įç´Ĭ
    0.14
    æķ´é½IJ
    0.14
    ç³»ç»ŁåĮĸ
    0.13
     regiment
    0.13
    ä¸Ģä¸Ŀä¸įèĭŁ
    0.13
    Activations Density 0.258%

    No Known Activations