© 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. 44093
    Prev
    Next
    INDEX
    Explanations

    combine, combine, combined

    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
    entif
    -0.12
    à§įà¦Ł
    -0.10
    lesia
    -0.09
    erÃŃa
    -0.09
    anka
    -0.09
    kena
    -0.09
    tera
    -0.09
    ureka
    -0.08
    ìį¨
    -0.08
    ivals
    -0.08
    POSITIVE LOGITS
    åľ¨ä¸Ģèµ·çļĦ
    0.09
    -sama
    0.08
    åľ¨ä¸Ģèµ·
    0.08
    tures
    0.07
    ingle
    0.07
    èµ·æĿ¥çļĦ
    0.07
    м
    0.07
     efforts
    0.07
    æĪIJä¸Ģ个
    0.06
    оеди
    0.06
    Activations Density 0.025%

    No Known Activations