© 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. 20398
    Prev
    Next
    INDEX
    Explanations

    mass spectrometry, mass units, particle mass

    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
    æ²¹éĩı
    -0.09
    annen
    -0.07
    ä¸įéĢĢ
    -0.07
    loff
    -0.07
    次æķ°
    -0.07
    ç«Ń
    -0.07
    çĻĮç»Ĩèĥŀ
    -0.07
    tero
    -0.07
    pread
    -0.07
    é«ĺæ°´å¹³
    -0.07
    POSITIVE LOGITS
     heavier
    0.10
    åĪĨåŃIJéĩı
    0.09
    è¾ĥéĩį
    0.09
    ç²ĴåŃIJ
    0.08
     przew
    0.08
    _tracker
    0.08
     particle
    0.08
    æ¯Ķéĩį
    0.07
    æ²īéĩį
    0.07
    weights
    0.07
    Activations Density 0.005%

    No Known Activations