© 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. 51661
    Prev
    Next
    INDEX
    Explanations

    evaporative drying / vapor towers

    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
    饨
    -0.07
     voting
    -0.07
     nightmares
    -0.07
    eia
    -0.07
    jong
    -0.07
    æĿ¯éħĴ
    -0.07
     nested
    -0.07
     assemb
    -0.07
    nested
    -0.07
    agos
    -0.07
    POSITIVE LOGITS
    èĴ¸åıij
    0.10
    æ°´æ±½
    0.10
     evapor
    0.09
    èĴ¸
    0.09
    æű
    0.08
    æ±½
    0.08
    湿润
    0.08
    æ°´
    0.08
     drying
    0.08
    湿
    0.08
    Activations Density 0.006%

    No Known Activations