© 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. 29894
    Prev
    Next
    INDEX
    Explanations

    pressure, column, water, diving, distribution

    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
    ÑıÑĤи
    -0.08
     Sparks
    -0.08
    羿
    -0.08
    steen
    -0.07
    brio
    -0.07
    æĴ®
    -0.07
    ursa
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    宿
    -0.07
    ITHER
    -0.07
    POSITIVE LOGITS
    æ°´åİĭ
    0.10
    åİĭ强
    0.09
     pressure
    0.09
    æ°´ä½į
    0.09
    åİĭåĬĽ
    0.09
    液ä½į
    0.09
     Pressure
    0.09
    çĽIJæ°´
    0.08
    Pressure
    0.08
    pressure
    0.08
    Activations Density 0.004%

    No Known Activations