© 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. 58080
    Prev
    Next
    INDEX
    Explanations

    Buddha, princess, incarnation, elf, consort

    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
    ÑĢев
    -0.09
    åľ¨åħ¨çľģ
    -0.08
    ç³Ł
    -0.08
    sour
    -0.08
     Raya
    -0.08
    æĴ²
    -0.07
    æ¯Ķåݻ年åIJĮæľŁ
    -0.07
    äºĪ
    -0.07
     Bong
    -0.07
    outh
    -0.07
    POSITIVE LOGITS
    æĪIJä½Ľ
    0.09
     consort
    0.08
    æ¦ľæł·
    0.07
    ä½į次
    0.07
     compassionate
    0.07
     vast
    0.07
    olk
    0.07
    寿åij½
    0.06
    æłĭæ¢ģ
    0.06
    丰满
    0.06
    Activations Density 0.001%

    No Known Activations