© 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. 49418
    Prev
    Next
    INDEX
    Explanations

    joining materials together

    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
     Bail
    -0.06
    轻工
    -0.06
    æĵ¾
    -0.06
    æĮĩåIJį
    -0.06
    haltung
    -0.06
    ekin
    -0.06
     volatility
    -0.06
     Bourbon
    -0.06
    æ¸ħæ¥ļäºĨ
    -0.06
    æ¸ħæĻ°åº¦
    -0.06
    POSITIVE LOGITS
    çī¢åĽº
    0.10
    修补
    0.10
     repairs
    0.10
    åľ¨ä¸Ģèµ·çļĦ
    0.09
    åĪ°ä¸Ģèµ·
    0.09
     ÑģоединениÑı
    0.09
    ç¼Ŀ
    0.09
    joining
    0.09
    è¿ŀæİ¥çļĦ
    0.09
     ná»iji
    0.09
    Activations Density 0.197%

    No Known Activations