© 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. 13762
    Prev
    Next
    INDEX
    Explanations

    medical journals and trials

    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
     <!--[
    -0.08
    ãĤ¹ãĥĪãĥ¼ãĥ«
    -0.07
    edm
    -0.07
    idup
    -0.07
    çĥŃ线çĶµè¯Ŀ
    -0.07
     annum
    -0.07
    åºķæĿ¿
    -0.06
    odaw
    -0.06
    عاد
    -0.06
    ذاÙĨ
    -0.06
    POSITIVE LOGITS
    大æ³ķ
    0.07
    retch
    0.07
    ailable
    0.07
    åŃ¦å£«
    0.07
    -icons
    0.06
     Bron
    0.06
     RANDOM
    0.06
    æľįåĬ¡
    0.06
    æ¹ĸ
    0.06
     دÙĦ
    0.06
    Activations Density 0.032%

    No Known Activations