© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34806
    Prev
    Next
    INDEX
    Explanations

    iid, independence, identical

    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
    ERING
    -0.08
    arine
    -0.07
    aque
    -0.07
    .getDefault
    -0.07
    Ùĩرب
    -0.07
    éķĤ
    -0.07
    ouser
    -0.07
     leve
    -0.07
    anical
    -0.06
    angible
    -0.06
    POSITIVE LOGITS
    个ä½ĵçļĦ
    0.09
     Independence
    0.08
    çĭ¬ç«ĭæĢ§
    0.08
     Individ
    0.08
    个个
    0.08
     iid
    0.08
     identical
    0.07
    ç»Łè®¡åѦ
    0.07
     independence
    0.07
     Sampling
    0.07
    Activations Density 0.018%

    No Known Activations