© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10835
    Prev
    Next
    INDEX
    Explanations

    standardized incidence ratios

    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
    ever
    -0.07
    ickness
    -0.07
    åħµçİĭ
    -0.07
    .Func
    -0.07
    è¾ŀ
    -0.06
     Por
    -0.06
    åĬłå·¥ä¼ģä¸ļ
    -0.06
     func
    -0.06
    æĸ©
    -0.06
    miny
    -0.06
    POSITIVE LOGITS
    ç»Łè®¡åѦ
    0.09
     statist
    0.09
     statistical
    0.09
     Statistical
    0.09
    ç»Łè®¡
    0.09
    çµ±è¨Ī
    0.08
     multin
    0.08
     expectation
    0.08
    女éĥİ
    0.08
     Expected
    0.08
    Activations Density 0.005%

    No Known Activations