© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39795
    Prev
    Next
    INDEX
    Explanations

    dissolving powders and tablets

    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
    çĭ©
    -0.08
    anford
    -0.07
    /mit
    -0.07
    åºĩ
    -0.07
    _AF
    -0.07
    chio
    -0.07
    contexts
    -0.07
    æµģçļĦ
    -0.07
    exter
    -0.07
    ouro
    -0.07
    POSITIVE LOGITS
    溶äºİæ°´
    0.11
    溶解
    0.11
    溶äºİ
    0.10
     dissolution
    0.10
     dissolved
    0.10
    溶
    0.09
    ç²īæľ«
    0.09
     sol
    0.09
     dissolve
    0.09
    åľ¨æ°´ä¸Ń
    0.08
    Activations Density 0.076%

    No Known Activations