© 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. 62967
    Prev
    Next
    INDEX
    Explanations

    band names, music albums

    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
    è¿Ļ人
    -0.07
    è¿Ļ天
    -0.07
    çĥŃå·´
    -0.07
    æŃ¤äºº
    -0.07
     worthless
    -0.06
    .nodeType
    -0.06
    è´¨
    -0.06
    èĤ²
    -0.06
    æĬ½
    -0.06
    èĢģ人家
    -0.06
    POSITIVE LOGITS
    æĪIJç«ĭæŶéĹ´
    0.11
    çļĦæĪIJåijĺ
    0.11
    æĪIJåĵ¡
    0.11
    æĪIJåijĺ
    0.10
     members
    0.10
    æĪIJç«ĭäºİ
    0.10
    mitglieder
    0.10
    åħ¨ä½ĵæĪIJåijĺ
    0.10
    æĪIJç«ĭ以æĿ¥
    0.09
    æĪIJåijĺçļĦ
    0.09
    Activations Density 0.471%

    No Known Activations