© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17053
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions 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
    elh
    -0.09
    usus
    -0.08
    æ³ķçŃī
    -0.07
    اء
    -0.07
    èī³ä¸½
    -0.07
    eln
    -0.07
     stil
    -0.07
    hés
    -0.07
     ë§IJìĿ´ëĭ¤
    -0.07
    aturan
    -0.07
    POSITIVE LOGITS
    öz
    0.07
    è¿Ļä¸İ
    0.06
    uen
    0.06
    æĬĢæľ¯ä¸İ
    0.06
    licas
    0.06
    æľīäºĭ
    0.06
    orra
    0.06
    ×ĺר
    0.06
     Kre
    0.06
    SEA
    0.06
    Activations Density 0.087%

    No Known Activations