© 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. 50393
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    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
    chu
    -0.08
    kun
    -0.08
    _HOOK
    -0.07
    æĮĩåIJį
    -0.07
    llib
    -0.07
    amn
    -0.07
    aky
    -0.07
     Bakal
    -0.07
    ä¿ĿéĻ©è´¹
    -0.07
    zny
    -0.07
    POSITIVE LOGITS
    eller
    0.07
    åıĸåħ¶
    0.07
     szemp
    0.07
    头çŃī
    0.06
     rient
    0.06
    -headed
    0.06
     earliest
    0.06
    ä»İ天
    0.06
     endeavor
    0.06
    ä½ľä¸ºä¸Ģç§į
    0.06
    Activations Density 0.012%

    No Known Activations