© 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. 30777
    Prev
    Next
    INDEX
    Explanations

    metabolic diseases and disorders

    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
    ông
    -0.08
    ä¸Ģ空
    -0.07
    æŀĦæĢĿ
    -0.07
    离éĢĢä¼ij
    -0.07
    _MACRO
    -0.07
    éĢĢä¼ij
    -0.07
     اÙĦدع
    -0.07
    onom
    -0.07
    éĻĦ
    -0.07
    æĽ´å¹´æľŁ
    -0.07
    POSITIVE LOGITS
    缺éĻ·
    0.09
    æĤ£åĦ¿
    0.08
     defects
    0.08
    çĶ·åŃ©
    0.08
     defect
    0.08
     childhood
    0.08
     crippling
    0.08
     disabilities
    0.08
     Childhood
    0.07
    éģĹä¼ł
    0.07
    Activations Density 0.225%

    No Known Activations