© 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. 38660
    Prev
    Next
    INDEX
    Explanations

    medical journal abbreviations

    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
    ðu
    -0.08
    ergestellt
    -0.07
    äºijå±±
    -0.07
    ç½ĹéĤ£
    -0.07
    交æīĢ
    -0.07
    VP
    -0.07
    ئÙĥ
    -0.07
    elai
    -0.07
     Reyn
    -0.06
    èĢĢ
    -0.06
    POSITIVE LOGITS
    åĩij
    0.08
    nose
    0.07
    osit
    0.07
    ÑħаÑĤÑĮ
    0.07
    rious
    0.07
    iform
    0.07
    å»Ī
    0.06
    ious
    0.06
    uml
    0.06
    UMB
    0.06
    Activations Density 0.001%

    No Known Activations