© 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. 21365
    Prev
    Next
    INDEX
    Explanations

    parts, cell, food, clients, tissue, user, light, host, dishes, apps

    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
    á»ĩt
    -0.08
    å¢Ł
    -0.08
    é¾ĻåŁİ
    -0.08
    taus
    -0.08
    otes
    -0.08
    æľīçļĦæĺ¯
    -0.08
    ضة
    -0.08
    ếm
    -0.07
    欢è¿İ大家
    -0.07
    forge
    -0.07
    POSITIVE LOGITS
     sense
    0.07
    ä½įäºİ
    0.07
    缴æİ¥æݥ触
    0.07
    åħ´è¡°
    0.06
     directly
    0.06
     direct
    0.06
     receives
    0.06
    zap
    0.06
    åľ¨åħ¶ä¸Ń
    0.06
    æł¹æį®åħ¶
    0.06
    Activations Density 0.100%

    No Known Activations