© 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. 13594
    Prev
    Next
    INDEX
    Explanations

    closing html tag

    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
    ieden
    -0.08
     FIXME
    -0.07
     sometime
    -0.07
    FIXME
    -0.07
    çļĦåľ°
    -0.07
     ÐŁÐ¾ÐºÐ°Ð·Ð°
    -0.07
    undur
    -0.07
     sedi
    -0.07
    åı¤æĢª
    -0.07
    ťaž
    -0.06
    POSITIVE LOGITS
    icka
    0.08
    "+"
    0.07
    åı¥è¯Ŀ说
    0.07
    çĿĢæĪijçļĦ
    0.07
    sci
    0.07
    avin
    0.07
    CharArray
    0.07
    å²ģçļĦåŃ©åŃIJ
    0.07
    etsy
    0.06
    cich
    0.06
    Activations Density 0.001%

    No Known Activations