© 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. 44971
    Prev
    Next
    INDEX
    Explanations

    Crimea and Jewish family

    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
    blick
    -0.08
    ervis
    -0.08
    è¿Ŀæ³ķåĴĮä¸įèī¯
    -0.08
    ä¸Ĭçĺ¾
    -0.08
    quine
    -0.08
    -regexp
    -0.07
    edale
    -0.07
     impun
    -0.07
    mpz
    -0.07
    èµĬ
    -0.07
    POSITIVE LOGITS
     wartime
    0.10
     during
    0.09
     durante
    0.09
    æĪĺä¹±
    0.09
    æĪĺçģ«
    0.09
    during
    0.08
     During
    0.08
     أثÙĨاء
    0.08
     Amid
    0.08
    åĬ¨èį¡
    0.08
    Activations Density 0.726%

    No Known Activations