© 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. 16147
    Prev
    Next
    INDEX
    Explanations

    limits and Windows Identity

    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
     [&
    -0.08
    _compiler
    -0.06
     ...(
    -0.06
    _restrict
    -0.06
     ï¼Ī
    -0.06
    Ùģض
    -0.06
    éĢļè¿ĩè¿Ļ个
    -0.06
    ãĢĤï¼Ī
    -0.06
    æĻ®æ£®
    -0.06
    uvi
    -0.06
    POSITIVE LOGITS
    ç¬ĶèĢħ
    0.08
    æĿŁ
    0.07
    eram
    0.07
    åĵģçļĦ
    0.07
    æ£ī
    0.07
    âĸ½
    0.06
    ikin
    0.06
     posto
    0.06
    TypeId
    0.06
    åĵģ
    0.06
    Activations Density 0.062%

    No Known Activations