© 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. 21082
    Prev
    Next
    INDEX
    Explanations

    brane biogenesis, bye Argentina

    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
    endor
    -0.07
    ׼×ķ׾
    -0.07
    äºĮæľŁ
    -0.07
    ä¸īéĩĮ
    -0.07
    getNode
    -0.07
    _None
    -0.07
    onais
    -0.07
    chand
    -0.07
    èĬ±é¦Ļ
    -0.07
    getError
    -0.06
    POSITIVE LOGITS
    ovina
    0.07
    áĢĽáĢ¾
    0.07
    urally
    0.07
    ICLE
    0.07
    inho
    0.07
    ุà¸ĩ
    0.07
    ัส
    0.07
    çݯèĬĤä¸Ń
    0.06
    eric
    0.06
     unfortunately
    0.06
    Activations Density 0.047%

    No Known Activations