© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55092
    Prev
    Next
    INDEX
    Explanations

    alpha(2)-adrenoceptor agonist

    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
    Negative Logits
    ês
    -0.07
     Colomb
    -0.07
    orio
    -0.07
    سÙĩ
    -0.07
    osaur
    -0.07
    heimer
    -0.07
    è¿Ļ个ä¸ĸçķĮ
    -0.06
    ä¸įç®Ģåįķ
    -0.06
    ookie
    -0.06
    modifica
    -0.06
    POSITIVE LOGITS
    ä¸Ģ说
    0.07
    leck
    0.07
     blat
    0.07
    arrass
    0.06
    обен
    0.06
    æıIJ示信æģ¯
    0.06
     ìĸµìłľ
    0.06
    ãĤĴæĬij
    0.06
    ÑĢаÑĤÑĮ
    0.06
    ÏĥÏĦι
    0.06
    Activations Density 0.084%

    No Known Activations