© 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. 7249
    Prev
    Next
    INDEX
    Explanations

    mucosal surfaces or linings

    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
    çĪ¬åĿ¡
    -0.07
    oming
    -0.07
    æĪIJåIJį
    -0.07
    ners
    -0.07
    shal
    -0.07
    ming
    -0.07
    èļģ
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    å¤§åľ°
    -0.06
    æݺæĿĤ
    -0.06
    POSITIVE LOGITS
    -covered
    0.08
     обол
    0.08
    èĦ±èIJ½
    0.08
    å±Ĥ
    0.08
     оболоÑĩки
    0.08
    å±ĤçļĦ
    0.07
     lining
    0.07
    -air
    0.07
    湿润
    0.07
    åħįåıĹ
    0.07
    Activations Density 0.042%

    No Known Activations