© 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. 22981
    Prev
    Next
    INDEX
    Explanations

    describing relationship or possession

    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
    æľīè´£
    -0.07
    æīĢèĥ½
    -0.07
     anywhere
    -0.07
    éĥ½æľīæīĢ
    -0.07
    åĪ°ä¸Ģ个
    -0.07
    è¿Ļæł·çļĦ
    -0.07
    ä½łä¸Ģ个
    -0.07
    Anywhere
    -0.06
    ä»Ģä¹Ī人
    -0.06
    æĽ´æĸ°æĹ¥æľŁ
    -0.06
    POSITIVE LOGITS
    aviest
    0.10
    liest
    0.10
     closest
    0.09
    closest
    0.08
     easiest
    0.08
    çļĦéĤ£ä¸ª
    0.08
     most
    0.08
    akest
    0.08
    оÑĤи
    0.08
    (s
    0.08
    Activations Density 0.305%

    No Known Activations