© 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. 7332
    Prev
    Next
    INDEX
    Explanations

    disjoint subsets summing to one

    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
    æľĢå·®
    -0.07
    置顶
    -0.07
     vang
    -0.07
    anen
    -0.07
    StatusCode
    -0.07
    blatt
    -0.07
    סק
    -0.06
     merit
    -0.06
    æĭīè¿ij
    -0.06
    è¿ijçļĦ
    -0.06
    POSITIVE LOGITS
    æĢ»åĴĮ
    0.14
    åĬłèµ·æĿ¥
    0.14
     complementary
    0.12
     total
    0.12
     TOTAL
    0.12
     Total
    0.11
    æĢ»
    0.11
    Total
    0.11
     totaling
    0.11
    åIJĪè¨Ī
    0.11
    Activations Density 0.056%

    No Known Activations