© 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. 33797
    Prev
    Next
    INDEX
    Explanations

    microcirculation, blood flow, perfusion

    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
    åħ¶èº«
    -0.07
    çļĦ身
    -0.07
    èģ
    -0.07
    éĺ²æ½®
    -0.07
    /plain
    -0.07
     conf
    -0.07
    æĹ©çĨŁ
    -0.07
    conf
    -0.07
     خش
    -0.07
    åı¬åĽŀ
    -0.06
    POSITIVE LOGITS
    æµģéĩı
    0.15
     circulation
    0.14
    ä¾Ľè¡Ģ
    0.13
    æµģéĩıçļĦ
    0.13
    æµģåIJij
    0.12
     arter
    0.12
    è¡Ģæµģ
    0.12
    arter
    0.12
     blood
    0.12
    åĬ¨èĦī
    0.12
    Activations Density 0.256%

    No Known Activations