© 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. 22726
    Prev
    Next
    INDEX
    Explanations

    correlated disorder, subscription costs, line search, apparent competition, meaning of terms, QR frequencies, vibrational spectra, feeding frequency, Texas, scale production

    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
    åıĸä¸ĭ
    -0.08
    odox
    -0.08
    æľīåı²
    -0.07
    夫åIJĽ
    -0.07
    ä¹ŁæľīäºĽ
    -0.07
     ditem
    -0.07
    èį·
    -0.07
    æĸ°æŃĮ
    -0.07
    ä¸Ńèĭ±æĸĩ
    -0.07
    æľºçŃī
    -0.07
    POSITIVE LOGITS
    ãģĵãģ¨ãĤĦ
    0.07
    )ãĢģ
    0.07
    pecia
    0.07
    ãģ§ãģĻãģĹ
    0.07
    ï¼īãĢģ
    0.06
    åĽ½è´¸
    0.06
    ipan
    0.06
    ":"","
    0.06
    è½°
    0.06
     Caldwell
    0.06
    Activations Density 1.056%

    No Known Activations