© 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. 45875
    Prev
    Next
    INDEX
    Explanations

    composite materials and compositions

    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
    åįłçĶ¨
    -0.06
    ä¸į误
    -0.06
    è³ĩ
    -0.06
    IPv
    -0.06
    alia
    -0.06
    aday
    -0.06
    ç«ĭä¸ĭ
    -0.06
    鼶
    -0.06
     lonely
    -0.06
    çī¹æ´¾
    -0.06
    POSITIVE LOGITS
     composition
    0.16
     compositions
    0.15
     Composition
    0.14
    Composition
    0.14
    composition
    0.14
     composición
    0.14
     composição
    0.13
     ÑģоÑģÑĤава
    0.13
    æ··åIJĪ
    0.13
     composed
    0.13
    Activations Density 0.188%

    No Known Activations