© 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. 47807
    Prev
    Next
    INDEX
    Explanations

    probability without replacement

    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
    orme
    -0.08
    efined
    -0.08
     GENERATED
    -0.07
    ÛĮÙģ
    -0.07
    åīįæµ·
    -0.07
    çļĦæĸ°çĶŁ
    -0.07
     ugl
    -0.07
    wart
    -0.07
    ä¸Ģå¸Ĩ
    -0.07
    Subscriber
    -0.07
    POSITIVE LOGITS
    ntag
    0.08
    æľīéĻIJ
    0.08
    ä¸įæĶ¾
    0.08
    icker
    0.08
    finite
    0.07
     finite
    0.07
    容
    0.07
    æł·æľ¬
    0.07
     sampling
    0.07
    iring
    0.07
    Activations Density 0.010%

    No Known Activations