© 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. 63278
    Prev
    Next
    INDEX
    Explanations

    supply and demand

    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
    saan
    -0.07
    à¹īำ
    -0.06
    æĹĹèĪ°åºĹ
    -0.06
    åİļå¾·
    -0.06
     Ristor
    -0.06
    gross
    -0.06
    inally
    -0.06
    ÑįнеÑĢго
    -0.06
    æīĵåį¡
    -0.06
    æݧèĤ¡åŃIJåħ¬åı¸
    -0.06
    POSITIVE LOGITS
    ä¾Ľç»Ļ
    0.14
    åĴĮéľĢæ±Ĥ
    0.13
     supply
    0.13
    ä¾Ľæ±Ĥ
    0.13
     Supply
    0.12
    ä¾Ľçµ¦
    0.12
    upply
    0.12
    ä¾ĽéľĢ
    0.12
    supply
    0.11
    Supply
    0.11
    Activations Density 0.031%

    No Known Activations