© 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. 2870
    Prev
    Next
    INDEX
    Explanations

    offshore installations

    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
    oliv
    -0.08
    astas
    -0.08
    оÑĢа
    -0.08
    ÑĨеле
    -0.08
    çĶļèĩ³ä¼ļ
    -0.08
    -hash
    -0.08
     herz
    -0.07
    yclopedia
    -0.07
    urette
    -0.07
    æ¯Ĥ
    -0.07
    POSITIVE LOGITS
    ers
    0.06
    avia
    0.06
    erring
    0.06
    esto
    0.06
    ovich
    0.06
    ting
    0.06
     Institutional
    0.06
     нед
    0.06
    强åĪ¶æݪæĸ½
    0.06
    iating
    0.06
    Activations Density 0.001%

    No Known Activations