© 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. 40634
    Prev
    Next
    INDEX
    Explanations

    HTML/XML meta tags and titles

    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
    peon
    -0.08
    話
    -0.08
    istring
    -0.08
    oulos
    -0.08
    éĢį
    -0.08
    telen
    -0.08
    æݨèįIJæľ¬ä¹¦
    -0.07
    ÙĬدات
    -0.07
    ķĮ
    -0.07
    ++++++++++++++++++++++++++++++++
    -0.07
    POSITIVE LOGITS
    å¾µ
    0.07
    rd
    0.06
    å¾ģ
    0.06
    å¤įåħ´
    0.06
     slate
    0.06
     preamble
    0.06
    ä¸Ģ课
    0.06
    k
    0.06
     eigen
    0.06
    ç«ĭä¸ĭ
    0.06
    Activations Density 0.009%

    No Known Activations