© 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. 50760
    Prev
    Next
    INDEX
    Explanations

    medical and research terms

    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
    emuk
    -0.07
     Doming
    -0.07
    меÑĢно
    -0.07
    ustin
    -0.06
    áĥIJáĥķ
    -0.06
     Manson
    -0.06
    ervas
    -0.06
    _cv
    -0.06
    æĶ¶éĽĨæķ´çIJĨ
    -0.06
    oto
    -0.06
    POSITIVE LOGITS
    ç®Ģ称
    0.11
    Ù°
    0.10
    ä¸ĭ称
    0.09
    簡稱
    0.09
     abbreviated
    0.08
    以ä¸ĭç®Ģ称
    0.08
    (SC
    0.08
    å°ģ
    0.07
    çıĪ
    0.07
    ä¿ĬæĿ°
    0.07
    Activations Density 0.549%

    No Known Activations