© 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. 25296
    Prev
    Next
    INDEX
    Explanations

    lipoprotein cholesterol

    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
    ble
    -0.07
     sprung
    -0.07
    onsor
    -0.07
    æ³īæ°´
    -0.07
    coder
    -0.07
     Spring
    -0.07
     vibr
    -0.07
    ä¸Ńæļij
    -0.07
    æĺ¥èĬ±
    -0.07
    öhn
    -0.07
    POSITIVE LOGITS
     cholesterol
    0.13
    èĥĨåĽºéĨĩ
    0.12
     LDL
    0.12
    è¡ĢèĦĤ
    0.11
     ÑħолеÑģÑĤ
    0.10
     kolesterol
    0.09
    olesterol
    0.09
     ÑħолеÑģÑĤеÑĢина
    0.09
     colesterol
    0.09
    åĬ¨èĦī硬åĮĸ
    0.09
    Activations Density 0.131%

    No Known Activations