© 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. 30837
    Prev
    Next
    INDEX
    Explanations

    optimal control and management

    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
    gara
    -0.08
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.07
    umpang
    -0.07
    idot
    -0.07
    /email
    -0.07
    HIR
    -0.07
    æ°ı
    -0.07
    inach
    -0.07
    upati
    -0.07
    éĩijåľ°
    -0.07
    POSITIVE LOGITS
    ting
    0.09
    авли
    0.08
    imal
    0.08
    -looking
    0.08
    /opt
    0.08
    erweise
    0.07
    æĪĸ被
    0.07
    æľ¨æĸ¯
    0.07
    rend
    0.07
    çļĦè·¯
    0.07
    Activations Density 0.010%

    No Known Activations