© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15157
    Prev
    Next
    INDEX
    Explanations

    MP RELEASE

    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
    æĥĭ
    -0.09
    æı
    -0.08
    enni
    -0.08
    дÑĢеÑģ
    -0.08
    ловÑĭе
    -0.07
    جد
    -0.07
    verband
    -0.07
    öv
    -0.07
    åĪĽæĸ°ä¸Ńå¿ĥ
    -0.07
    ChangeEvent
    -0.07
    POSITIVE LOGITS
    utt
    0.07
    æĹłéĩı
    0.07
    åĢ¼æĺ¯
    0.06
    ensos
    0.06
    éªĨ
    0.06
    æķ°ä½į
    0.06
     contested
    0.06
    丽
    0.06
    ght
    0.06
     digits
    0.06
    Activations Density 0.006%

    No Known Activations