© 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. 33206
    Prev
    Next
    INDEX
    Explanations

    us states and their associated topics

    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
    é¸Łå·¢
    -0.08
    UNCT
    -0.08
    ä¸Ń央纪å§Ķ
    -0.08
    artig
    -0.08
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.07
    INGS
    -0.07
    社éķ¿
    -0.07
    escu
    -0.07
    åĽ½åľŁèµĦæºIJå±Ģ
    -0.07
    æĸĩåĮĸå¹¿åľº
    -0.07
    POSITIVE LOGITS
    ä¸Ģåľ°
    0.08
     legislature
    0.08
    mano
    0.08
     Legislature
    0.07
    åħ¨åŁŁ
    0.07
    çİĩåħĪ
    0.07
    -specific
    0.07
    åĩºåı°äºĨ
    0.07
    人æ°ijæĶ¿åºľ
    0.07
    åħ¨çľģ
    0.07
    Activations Density 0.332%

    No Known Activations