© 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. 22985
    Prev
    Next
    INDEX
    Explanations

    structural nested models

    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
    hex
    -0.07
    æŀķ
    -0.07
     hex
    -0.07
     soli
    -0.06
    åIJĪä½ľåĬŀåѦ
    -0.06
    éĤ»è¿ij
    -0.06
    ç½²
    -0.06
     soi
    -0.06
     adjacent
    -0.06
    深度åIJĪä½ľ
    -0.06
    POSITIVE LOGITS
    artal
    0.09
     mart
    0.09
    æ±ŁåŁİ
    0.08
    åĴĮé£İéĻ©
    0.08
     accumulating
    0.08
    ÑĢовÑģкий
    0.08
    é£İéĻ©æݧåĪ¶
    0.08
    holt
    0.08
     Paige
    0.08
    -basket
    0.08
    Activations Density 0.006%

    No Known Activations