© 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. 28465
    Prev
    Next
    INDEX
    Explanations

    time, all, boot, because, that, as, those

    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
    figcaption
    -0.08
    illot
    -0.08
    loth
    -0.08
    ä¹ĭæģĭ
    -0.08
    æĿ¡è¯Ħ论
    -0.08
    éĥ¨çº§
    -0.07
    enge
    -0.07
    лиÑģ
    -0.07
    aver
    -0.07
    ợ
    -0.07
    POSITIVE LOGITS
    earing
    0.07
    åħĦå¼Ł
    0.06
     Swarm
    0.06
    èĭ¦çĵľ
    0.06
    ä¸įå¿«
    0.06
    Õ¡Õ£
    0.06
     Direct
    0.06
     direct
    0.06
    ijan
    0.06
    缴æİ¥çļĦ
    0.06
    Activations Density 0.242%

    No Known Activations