© 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. 15468
    Prev
    Next
    INDEX
    Explanations

    titles and questions with specific follows

    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
    æ¯ĶæĪij们
    -0.07
    linky
    -0.07
    baugh
    -0.07
     sheds
    -0.07
    STYPE
    -0.07
    alach
    -0.07
    åľ¨æĪijçľĭæĿ¥
    -0.07
     gesta
    -0.07
    éħİ
    -0.06
    ory
    -0.06
    POSITIVE LOGITS
    roph
    0.07
    ç¿Ł
    0.07
    ennis
    0.06
    icias
    0.06
    æ¿
    0.06
    æ·¼
    0.06
    &_
    0.06
    èµ°
    0.06
    æīįæĺ¯
    0.06
    енÑĮ
    0.06
    Activations Density 0.001%

    No Known Activations