© 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. 11892
    Prev
    Next
    INDEX
    Explanations

    astronomical observations and tests

    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
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.08
    -lite
    -0.08
    容
    -0.08
    воÑĢÑı
    -0.08
    itoris
    -0.08
     ÙĪÙĦÙĥ
    -0.07
     liking
    -0.07
    ä¸įåĸĦ
    -0.07
    aso
    -0.07
    寸
    -0.07
    POSITIVE LOGITS
    ä¸ŃçļĦåºĶçĶ¨
    0.08
     tests
    0.08
     experiments
    0.08
    éĹ²
    0.07
     comparisons
    0.07
    нибÑĥдÑĮ
    0.07
    tests
    0.07
     comparative
    0.07
    æ¯Ķè¾ĥå¤ļ
    0.07
     test
    0.07
    Activations Density 0.025%

    No Known Activations