© 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. 26003
    Prev
    Next
    INDEX
    Explanations

    is a

    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
    -BEGIN
    -0.08
    ovin
    -0.07
    -valu
    -0.07
    WithData
    -0.07
    utz
    -0.07
     Richards
    -0.07
    èĮĥåĽ´çļĦ
    -0.07
    ÙĩÙĨ
    -0.07
    请ç«ĭåį³
    -0.07
    累累
    -0.07
    POSITIVE LOGITS
    æļĩ
    0.07
    itera
    0.07
    èĪİ
    0.06
    使å®ĥ
    0.06
    稿
    0.06
    æķħ人
    0.06
    ä¹Łæĺ¯è¿Ļæł·
    0.06
    ios
    0.06
    æĸŃ
    0.06
    w
    0.06
    Activations Density 0.007%

    No Known Activations