© 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. 45649
    Prev
    Next
    INDEX
    Explanations

    Nash equilibrium

    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
    _ent
    -0.07
    erson
    -0.07
     Panas
    -0.07
    luv
    -0.07
    åĴĮä¸į足
    -0.07
    æ·¼
    -0.07
    ä½ľæģ¯æŶéĹ´
    -0.07
    funcs
    -0.06
    uta
    -0.06
    linear
    -0.06
    POSITIVE LOGITS
    ä¼¼
    0.08
    osten
    0.07
    çĽĪäºı
    0.07
     roma
    0.07
    Schedulers
    0.07
    èĬĴ
    0.07
    haltung
    0.07
     misc
    0.06
    halt
    0.06
     Mills
    0.06
    Activations Density 0.029%

    No Known Activations