© 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. 56516
    Prev
    Next
    INDEX
    Explanations

    medical conditions and professional contexts

    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
    ÑĢÑĥжи
    -0.08
    inarie
    -0.08
    misc
    -0.07
    ä½ļåIJį
    -0.07
    以åıĬåħ¶ä»ĸ
    -0.07
    .ak
    -0.07
    èĭ±æĸĩåIJįåŃĹ
    -0.07
    ä¼°è¨Ī
    -0.07
    adang
    -0.07
    å¾Ī好çļĦ
    -0.07
    POSITIVE LOGITS
     [âĢ¦]
    0.11
     [âĢ¦
    0.09
     [...]
    0.09
     (âĢ¦)
    0.09
     (...)
    0.09
    0.09
    Âł
    0.08
    0.07
    èĩªä¸ª
    0.07
    âĢĮ
    0.07
    Activations Density 0.107%

    No Known Activations