© 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. 50185
    Prev
    Next
    INDEX
    Explanations

    water and oxygen reactions

    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
     עצ
    -0.08
    kund
    -0.08
    æľīç»ıéªĮ
    -0.08
     lợ
    -0.08
    μον
    -0.07
     áĥIJáĥ¡
    -0.07
    suite
    -0.07
    ovia
    -0.07
    loc
    -0.07
    -Americ
    -0.07
    POSITIVE LOGITS
    ewater
    0.07
    çĶ¨æ°´
    0.07
    绵
    0.07
     formed
    0.06
    Ùģات
    0.06
    åĩij
    0.06
    æ¶Ī
    0.06
     matrim
    0.06
    éĨĩ
    0.06
    ç½
    0.06
    Activations Density 0.001%

    No Known Activations