© 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. 15280
    Prev
    Next
    INDEX
    Explanations

    maintain consistency or state

    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
    æł·çļĦ
    -0.08
    ophone
    -0.08
    ़
    -0.07
    AVAILABLE
    -0.07
    ิà¸ķิ
    -0.07
    inct
    -0.07
    zeitig
    -0.06
    mund
    -0.06
     decisive
    -0.06
    Ĩ
    -0.06
    POSITIVE LOGITS
    OrUpdate
    0.11
    gomery
    0.08
    enance
    0.08
    åĴĮåıijå±ķ
    0.08
    ä¸įä½ı
    0.08
    รัà¸ģษา
    0.08
    æĤ´
    0.08
    ذج
    0.08
    /disable
    0.08
     hidup
    0.08
    Activations Density 0.027%

    No Known Activations