© 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. 40271
    Prev
    Next
    INDEX
    Explanations

    worldwide, global, earth

    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¨åħ¨çľģ
    -0.09
    åľ¨åħ¨å¸Ĥ
    -0.08
     municipale
    -0.08
    åIJij社ä¼ļ
    -0.08
     Auton
    -0.08
    åľ¨åĨľæĿij
    -0.07
     Cheney
    -0.07
    çĤ¹çĤ¹æ»´æ»´
    -0.07
    åľ¨çľģ
    -0.07
     Whitney
    -0.07
    POSITIVE LOGITS
    çļĦåħ¨çIJĥ
    0.20
     global
    0.20
    åħ¨çIJĥ
    0.19
    çŃīåĽ½éĻħ
    0.19
    æĺ¯åħ¨çIJĥ
    0.19
     worldwide
    0.18
    为åħ¨çIJĥ
    0.17
    global
    0.17
     world
    0.17
     гло
    0.16
    Activations Density 0.699%

    No Known Activations