© 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. 65504
    Prev
    Next
    INDEX
    Explanations

    size scaling and reduction

    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
    aldo
    -0.08
    ÙĪÙħÙĬ
    -0.08
    èIJ¤çģ«
    -0.07
     disag
    -0.07
    ngo
    -0.07
    äºĴéĢļ
    -0.07
    åĨįæĹł
    -0.07
    undry
    -0.07
    azo
    -0.07
    åĮºåĮº
    -0.07
    POSITIVE LOGITS
    缩å°ı
    0.10
    æ¯Ķä¾ĭçļĦ
    0.10
     size
    0.09
    æ¯Ķä¾ĭ
    0.09
    æĶ¾å¤§
    0.08
     enlargement
    0.08
    .localScale
    0.08
    size
    0.08
     resizing
    0.08
     Size
    0.08
    Activations Density 0.002%

    No Known Activations