© 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. 41671
    Prev
    Next
    INDEX
    Explanations

    mathematical distance calculations with sqrt

    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
    ÑĢани
    -0.09
    éļ·
    -0.08
    bdd
    -0.08
    -bre
    -0.08
    uling
    -0.08
    çłĶ究对象
    -0.08
    SSION
    -0.08
    妩
    -0.08
    पà¥ģर
    -0.08
    zeci
    -0.07
    POSITIVE LOGITS
    loch
    0.07
    身
    0.06
    ç³»çļĦ
    0.06
    åħ¨æĸ¹ä½į
    0.06
    æĶĢçĪ¬
    0.06
    sum
    0.06
     perse
    0.06
    entic
    0.06
    乡
    0.06
     distances
    0.06
    Activations Density 0.003%

    No Known Activations