© 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. 20517
    Prev
    Next
    INDEX
    Explanations

    turbulent flows and turbulence

    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
    ode
    -0.09
    éĢĢåĽŀ
    -0.08
    ocere
    -0.08
     Maus
    -0.08
    ä¿ĿæĬ¤å¥½
    -0.08
    BIND
    -0.08
    otp
    -0.08
    ovens
    -0.07
    ç»Ŀ伦
    -0.07
    è£ħ帧
    -0.07
    POSITIVE LOGITS
     turbulence
    0.09
     turbulent
    0.09
    sampling
    0.08
    Sampling
    0.08
     Sampling
    0.07
     gust
    0.07
    æ±Łæ¹ĸ
    0.07
     sampling
    0.07
    æ¹
    0.07
    æ´»è·ĥ
    0.07
    Activations Density 0.009%

    No Known Activations