© 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. 8601
    Prev
    Next
    INDEX
    Explanations

    and or and

    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
    å¯ĵ
    -0.06
    art
    -0.06
    建
    -0.06
    羣æŃ£çļĦ
    -0.06
    åijĬ
    -0.06
    ä¸Ģç»ı
    -0.06
    è¯Ŀ
    -0.06
    pon
    -0.05
    _
    -0.05
    çĶŁæĪIJ
    -0.05
    POSITIVE LOGITS
    rogen
    0.09
    éĥ½ä¼ļåľ¨
    0.08
    taan
    0.08
     Pregun
    0.08
     Livingston
    0.08
     Catégorie
    0.08
    ients
    0.08
    uos
    0.08
    .xhtml
    0.08
    ìĿ´ìĸ´
    0.07
    Activations Density 0.147%

    No Known Activations