© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 31774
    Prev
    Next
    INDEX
    Explanations

    technical terms and chinese characters

    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
    åĮĻ
    -0.08
    irut
    -0.08
    éģĤ
    -0.07
    balances
    -0.07
    bel
    -0.07
    hoff
    -0.07
     balances
    -0.07
    Ģ
    -0.07
    ķĮ
    -0.07
    é¡»
    -0.07
    POSITIVE LOGITS
    ihan
    0.08
    hado
    0.07
    羯
    0.06
    INES
    0.06
    è°ĥçłĶåijĺ
    0.06
    åĮĸåİ¿
    0.06
    çϾäºĭ
    0.06
    elaar
    0.06
     Bundy
    0.06
    åĮĸ
    0.06
    Activations Density 0.004%

    No Known Activations