© 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. 48970
    Prev
    Next
    INDEX
    Explanations

    emergency services and responses

    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
    ç´§äºĨ
    -0.08
    à¹Ģรืà¹Īà¸Ńยà¹Ĩ
    -0.08
    quam
    -0.08
    çīĩæľº
    -0.08
    aian
    -0.08
    ominated
    -0.08
    itional
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    _tuple
    -0.08
    åĬŀåħ¬åİħ
    -0.07
    POSITIVE LOGITS
    æĥħåĨµä¸ĭ
    0.10
    atory
    0.08
    licherweise
    0.07
    é¢ijåıij
    0.07
    /disable
    0.07
    çĬ¶æĢģä¸ĭ
    0.07
    رÙģ
    0.07
    åĮ»çĸĹ
    0.07
    çŃł
    0.06
    çī©èµĦ
    0.06
    Activations Density 0.019%

    No Known Activations