© 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. 22977
    Prev
    Next
    INDEX
    Explanations

    div id="webpart", class, Entity, According, .json, public var, Dim

    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
    .Active
    -0.06
    actively
    -0.06
    itta
    -0.06
    åį°è¯ģ
    -0.06
    æİ¥ä¸ĭ
    -0.06
     /*!<
    -0.06
    aille
    -0.06
    对åºĶ
    -0.06
    为äºĨ让
    -0.06
    IBC
    -0.06
    POSITIVE LOGITS
     totiž
    0.09
     przecież
    0.08
    æĸ¯åŁº
    0.08
     bowiem
    0.08
     pourtant
    0.07
    à¹Ħà¸ĩ
    0.07
     enim
    0.07
    unya
    0.07
    _MAY
    0.07
    ÑĢд
    0.07
    Activations Density 1.272%

    No Known Activations