© 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. 63915
    Prev
    Next
    INDEX
    Explanations

    EXPECT threshold, test

    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
    çľ¼çĿģçĿģ
    -0.08
    oners
    -0.08
    æľĢæĸ°ç«łèĬĤ
    -0.08
    ystems
    -0.08
    ç½Ħ
    -0.08
    cdb
    -0.08
    æĥħç»ĵ
    -0.07
    åѦçĶŁå®¶éķ¿
    -0.07
    çµĦåIJĪ
    -0.07
    (es
    -0.07
    POSITIVE LOGITS
     computed
    0.07
    computed
    0.06
    çĽĪ
    0.06
    çĿ¿æĻº
    0.06
    ized
    0.06
    éħĴç²¾
    0.06
    åħ¬å¼ı
    0.06
    管家
    0.06
    edReader
    0.06
     adjusted
    0.06
    Activations Density 0.004%

    No Known Activations