© 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. 8136
    Prev
    Next
    INDEX
    Explanations

    random variable probability bounds

    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
     inse
    -0.07
    VEC
    -0.07
    ovid
    -0.06
     Pompeo
    -0.06
    çĥŃéŨæĸĩç«ł
    -0.06
     Viv
    -0.06
    otec
    -0.06
    áº
    -0.06
    ä¸ŃåĽ½å¤§éĻĨ
    -0.06
    cope
    -0.06
    POSITIVE LOGITS
    asser
    0.08
    çĤİ
    0.08
    ä¸Ĭ大
    0.08
     exponentially
    0.08
     Äijuôi
    0.08
    æļ´éľ²
    0.07
    å°¾éĥ¨
    0.07
    Tail
    0.07
    çĥĪæĹ¥
    0.07
    éªĭ
    0.07
    Activations Density 0.008%

    No Known Activations