© 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. 27789
    Prev
    Next
    INDEX
    Explanations

    nitrate, nitric oxide, nitrogen

    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
    abouts
    -0.08
    OrNull
    -0.08
    æĢ»æ¯Ķ
    -0.08
     Bronx
    -0.08
    å¥Ķèµ´
    -0.07
    ÏĢον
    -0.07
    orida
    -0.07
    çļĦ人类
    -0.07
    мога
    -0.07
    以赴
    -0.07
    POSITIVE LOGITS
    zeb
    0.07
    æµı
    0.07
    绥
    0.07
    omber
    0.07
    头æĿ¡
    0.07
    åºĦ
    0.07
    .microsoft
    0.07
    eeper
    0.06
    ìķĶ
    0.06
    çľ¼èĬ±
    0.06
    Activations Density 0.011%

    No Known Activations