© 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. 18383
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and actions

    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
    çļĦä¸Ģç§įæĸ¹å¼ı
    -0.08
    ä¹ĭæĦŁ
    -0.08
    çļĦä¸Ģç§į
    -0.07
    çĻ»è®°æīĭç»Ń
    -0.07
     عبارة
    -0.07
    è¿Ļåı«
    -0.07
    认为æĺ¯
    -0.06
    çļĦä¸Ģ種
    -0.06
    åĬªåĬĽåģļåĪ°
    -0.06
    èµ·åĪ°
    -0.06
    POSITIVE LOGITS
    áĥ£áĥľ
    0.08
    缸æī£
    0.08
     jossa
    0.07
    Ùijر
    0.07
    eller
    0.07
    çĥŃæĴŃ
    0.06
    åįģåĪĨçļĦ
    0.06
    æĬĬæĪij们
    0.06
    íĥķ
    0.06
     подÑĢазÑĥме
    0.06
    Activations Density 0.748%

    No Known Activations