© 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. 10901
    Prev
    Next
    INDEX
    Explanations

    pH and acidity measurements

    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
    æĢ»éĩı
    -0.08
    ëħķ
    -0.08
     à¤Ńर
    -0.07
    à¸Ĭà¸Ļ
    -0.07
    ikasi
    -0.07
     ($.
    -0.07
     vectors
    -0.07
    _fin
    -0.07
    æīijéĿ¢
    -0.07
    æŁ¥çľĭåħ¨éĥ¨
    -0.07
    POSITIVE LOGITS
     Acid
    0.09
     acid
    0.08
    éħ¸
    0.08
    éħ¸æĢ§
    0.08
     midway
    0.08
    seudo
    0.07
     acidic
    0.07
     pH
    0.07
     acids
    0.07
    acid
    0.07
    Activations Density 0.001%

    No Known Activations