© 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. 16652
    Prev
    Next
    INDEX
    Explanations

    elements and chemical formulas

    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
    æīĢè°ĵ
    -0.07
    alth
    -0.07
    iaux
    -0.06
    éļĶå£ģ
    -0.06
    eming
    -0.06
     weekday
    -0.06
    款
    -0.06
    æ°´çģ«
    -0.06
    æľīçļĦ
    -0.06
    ä¸Ģ款
    -0.06
    POSITIVE LOGITS
    .charCodeAt
    0.08
    å®Ŀå®Ŀ们
    0.08
    ÑģÑĤÑı
    0.07
    acap
    0.07
    ingin
    0.07
    Ø®ÙĬÙĨ
    0.07
    鼰
    0.07
     czar
    0.07
    dua
    0.07
     atoms
    0.07
    Activations Density 0.030%

    No Known Activations