© 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. 17527
    Prev
    Next
    INDEX
    Explanations

    also, again, same

    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
    apsed
    -0.07
    èħ¾
    -0.07
    arde
    -0.07
    anted
    -0.07
    eway
    -0.07
    edata
    -0.07
    resse
    -0.06
    æĪijçļĦå°ı
    -0.06
    awy
    -0.06
    andan
    -0.06
    POSITIVE LOGITS
    same
    0.10
     same
    0.10
    à¹Ģà¸Ķียวà¸ģัà¸Ļ
    0.10
    åIJĮä¸Ģ个
    0.09
    Same
    0.09
     aynı
    0.09
    åIJĮæł·çļĦ
    0.08
    缸åIJĮ
    0.08
     SAME
    0.08
     Same
    0.08
    Activations Density 0.087%

    No Known Activations