© 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. 2424
    Prev
    Next
    INDEX
    Explanations

    byte values, bit masks

    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
    åįģäºĮæĿ¡
    -0.09
    aldas
    -0.08
    åĩłæĿ¡
    -0.08
    jang
    -0.08
    åįģæĿ¡
    -0.08
     Kard
    -0.08
    AdapterFactory
    -0.08
    arkin
    -0.07
    emand
    -0.07
     strat
    -0.07
    POSITIVE LOGITS
    第ä¸Ģ个
    0.08
    çļĦ第ä¸Ģ个
    0.07
    毫
    0.07
     Maiden
    0.07
    第ä¸Ģä½į
    0.06
    isNaN
    0.06
    gte
    0.06
    ละ
    0.06
     modulo
    0.06
    odle
    0.06
    Activations Density 0.011%

    No Known Activations