© 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. 19709
    Prev
    Next
    INDEX
    Explanations

    Elon Musk claims, Dark Souls, Jean-Paul Sartre

    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
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    ehold
    -0.08
    chend
    -0.08
    à®°à®ļ
    -0.08
    ابÛĮ
    -0.08
    acons
    -0.08
    entic
    -0.07
     ôt
    -0.07
     daqu
    -0.07
     EITHER
    -0.07
    POSITIVE LOGITS
    enberg
    0.08
    ç¬
    0.06
     stip
    0.06
    èĴĤ
    0.06
    illian
    0.06
    çļĦä¸Ģ项éĩįè¦ģ
    0.06
    emberg
    0.06
    -
    0.06
    isten
    0.06
     fame
    0.06
    Activations Density 0.087%

    No Known Activations