© 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. 45419
    Prev
    Next
    INDEX
    Explanations

    singleton instance initialization

    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
    enis
    -0.08
    对æĸ¹çļĦ
    -0.07
    å¾Ĺå¿ĥ
    -0.07
     Viola
    -0.07
    utum
    -0.07
    çŃ¾
    -0.07
    çľ¼çĿģçĿģ
    -0.07
     gamb
    -0.07
    è¿ĻäºĽåĽłç´ł
    -0.07
    天éŃĶ
    -0.07
    POSITIVE LOGITS
    -global
    0.09
     global
    0.09
     getInstance
    0.09
    singleton
    0.09
    åħ¨çIJĥ
    0.08
    åħ¨çIJĥçļĦ
    0.08
     globally
    0.08
    çŃĭ
    0.08
    _instances
    0.08
    Global
    0.08
    Activations Density 0.251%

    No Known Activations