© 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. 48464
    Prev
    Next
    INDEX
    Explanations

    HTML link anchors

    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
    uilder
    -0.07
    >(()
    -0.07
    uggy
    -0.07
    riend
    -0.07
    tester
    -0.07
    娲
    -0.07
    ç½ij绾æĬĢæľ¯
    -0.07
    ราà¸Ļ
    -0.07
    olds
    -0.06
    legacy
    -0.06
    POSITIVE LOGITS
    berge
    0.08
    ä¼ĹæīĢåij¨çŁ¥
    0.07
    обÑĢа
    0.07
     Merrill
    0.07
    IFY
    0.06
    berg
    0.06
     Levin
    0.06
    åĬłæĭ¿å¤§
    0.06
    alama
    0.06
     ReturnType
    0.06
    Activations Density 0.132%

    No Known Activations