© 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. 50837
    Prev
    Next
    INDEX
    Explanations

    carboxylic acid

    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
    ´
    -0.08
    ersh
    -0.08
    符
    -0.07
    ÙİÙijا
    -0.07
    tip
    -0.07
    Åijd
    -0.07
    èĮ¸
    -0.07
    å¦ĤåĪĿ
    -0.07
    空èĻļ
    -0.07
    çļ®çIJĥ
    -0.07
    POSITIVE LOGITS
    éħ¸åĮĸ
    0.09
    éħ¸çļĦ
    0.08
     acid
    0.07
     acidity
    0.07
    éħ¸
    0.07
     tart
    0.07
     acids
    0.07
    usine
    0.07
    æĮ½
    0.07
     Acid
    0.07
    Activations Density 0.018%

    No Known Activations