© 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. 45977
    Prev
    Next
    INDEX
    Explanations

    medical terms and technical standards

    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
    usercontent
    -0.09
    /{}/
    -0.09
     lõi
    -0.09
     ÐĹве
    -0.08
    parg
    -0.08
    Ú¯ÙĦ
    -0.08
    еÑĢна
    -0.08
    erset
    -0.08
    çľ¼èĬ±ç¼Ń
    -0.08
    æĸ°æŃĮ
    -0.08
    POSITIVE LOGITS
    ↵
    0.08
    ↵↵
    0.08
    č↵
    0.07
    ä»Ģä¹ĪæĦıæĢĿ
    0.07
     (
    0.07
    ↵ ↵
    0.06
    âĢij
    0.06
     ↵
    0.06
    \n
    0.06
    0.06
    Activations Density 11.098%

    No Known Activations