© 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. 12550
    Prev
    Next
    INDEX
    Explanations

    preterm birth, delivery, labor

    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
    ä¸īå¹´æĿ¥
    -0.08
    è¦
    -0.07
    ìĩł
    -0.07
    metics
    -0.07
    zik
    -0.07
    raud
    -0.07
    æıĸ
    -0.07
    /Grid
    -0.06
    ichtung
    -0.06
    è¿ĻåĿĹ
    -0.06
    POSITIVE LOGITS
    æĹ©äº§
    0.11
    venz
    0.09
     premature
    0.09
    æĹ©
    0.09
    å¼Ģåıijå·¥ç¨ĭå¸Ī
    0.08
    æıIJæĹ©
    0.08
     gest
    0.08
    èĥİ
    0.07
    Early
    0.07
     fetal
    0.07
    Activations Density 0.052%

    No Known Activations