© 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. 17429
    Prev
    Next
    INDEX
    Explanations

    boolean false assignments

    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
    usta
    -0.07
    arik
    -0.07
    odu
    -0.07
    .elapsed
    -0.07
    lesa
    -0.07
    alez
    -0.06
    pai
    -0.06
    絡
    -0.06
    phant
    -0.06
    inea
    -0.06
    POSITIVE LOGITS
    设为é¦ĸ页
    0.08
    ä¸Ĭä¸į
    0.08
    åĬĽåº¦
    0.08
    æŃ»åIJİ
    0.08
     overrides
    0.07
    æĮĩå®ļ
    0.07
     dite
    0.07
    asar
    0.07
    åľ¨å¾Ī大ç¨ĭ度ä¸Ĭ
    0.07
     opt
    0.07
    Activations Density 0.133%

    No Known Activations