© 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. 38722
    Prev
    Next
    INDEX
    Explanations

    fluid flow 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
    ç¡Ĵ
    -0.09
    çĻ»å±±
    -0.08
    çħ§å°Ħ
    -0.08
    çĨĶçĤ¹
    -0.07
    çĴĢ
    -0.07
    itele
    -0.07
    æ²īçĶ¸çĶ¸
    -0.07
    æIJĸ
    -0.07
    å¤§åľ°éľĩ
    -0.07
     radios
    -0.07
    POSITIVE LOGITS
     turbulence
    0.14
     turbulent
    0.13
    æ¹
    0.13
     fluid
    0.13
    flow
    0.12
    æµģåĬ¨
    0.12
    æµģä½ĵ
    0.12
    涡
    0.12
    æµģéĢŁ
    0.12
     flow
    0.12
    Activations Density 0.045%

    No Known Activations