© 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. 17331
    Prev
    Next
    INDEX
    Explanations

    programming concepts

    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
    ä¸įåºĶæ±Ĥ
    -0.07
    æĥħ
    -0.07
    atis
    -0.07
    aty
    -0.07
    缸è¾ĥäºİ
    -0.07
    æĪ¿åĨħ
    -0.07
    åĮºåĪ«äºİ
    -0.07
    èĢĮéĿŀ
    -0.07
    agia
    -0.06
    oje
    -0.06
    POSITIVE LOGITS
    ä¸İä¹ĭ
    0.13
    两èĢħ
    0.12
     ones
    0.11
     vice
    0.11
    åıįä¹ĭ
    0.10
    åħ©èĢħ
    0.10
    两èĢħçļĦ
    0.09
    äºĮèĢħ
    0.09
     theirs
    0.08
     thereof
    0.08
    Activations Density 0.624%

    No Known Activations