© 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. 9513
    Prev
    Next
    INDEX
    Explanations

    medical or technical examination

    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
     degusta
    -0.09
     asisti
    -0.09
    åľ¨åĨħçļĦ
    -0.09
    éĥ½åºĶ该
    -0.08
    éĥ½åįģåĪĨ
    -0.07
    éĥ½æ¯Ķè¾ĥ
    -0.07
    ouce
    -0.07
    éĥ½å¿ħé¡»
    -0.07
     gewesen
    -0.07
     Ø¥ÙĨÙĩ
    -0.07
    POSITIVE LOGITS
     can
    0.09
     infatti
    0.09
     would
    0.09
     totiž
    0.09
    ç»ĵæŀľè¡¨æĺİ
    0.08
     may
    0.08
    çłĶ究表æĺİ
    0.08
     λοι
    0.08
     is
    0.08
     (âĢ¦)
    0.08
    Activations Density 0.987%

    No Known Activations