© 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. 46117
    Prev
    Next
    INDEX
    Explanations

    airflow and aerodynamics

    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
    åľ°éĽ·
    -0.08
    åıĺè´¨
    -0.07
    Bright
    -0.07
    bright
    -0.07
     chemistry
    -0.07
    åľŁå£¤ä¸Ń
    -0.07
    batim
    -0.07
    解æ¯Ĵ
    -0.07
     brighter
    -0.07
     Bloom
    -0.07
    POSITIVE LOGITS
     airflow
    0.11
    è¿İé£İ
    0.11
     aer
    0.11
    æ°Ķæµģ
    0.10
    éĺ»åĬĽ
    0.10
    è¿İéĿ¢
    0.10
     Profil
    0.09
    è¥Ł
    0.09
     bluff
    0.09
    æµģ线
    0.09
    Activations Density 0.050%

    No Known Activations