© 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. 29520
    Prev
    Next
    INDEX
    Explanations

    United Nations

    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
    æ±
    -0.07
    äºİä¸Ģ
    -0.07
    alement
    -0.07
    atism
    -0.07
    TabControl
    -0.06
     versa
    -0.06
    ountain
    -0.06
    uchy
    -0.06
    çĤ¹åIJİ
    -0.06
    æīĭ
    -0.06
    POSITIVE LOGITS
    requ
    0.08
     ÐŀÐŀÐĿ
    0.08
    åĴĮåĽ½éĻħ
    0.08
    çļĦåĽ½éĻħ
    0.08
    æķĻç§ijæĸĩ
    0.08
    çŃīåĽ½éĻħ
    0.08
    миÑĢ
    0.07
    iversal
    0.07
     views
    0.07
    forgettable
    0.07
    Activations Density 0.026%

    No Known Activations