© 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. 24827
    Prev
    Next
    INDEX
    Explanations

    approximation and mathematical notation

    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
    izzi
    -0.08
    adona
    -0.08
     оÑĤв
    -0.08
    èģĶç³»åľ°åĿĢ
    -0.07
    IVI
    -0.07
    eaux
    -0.07
    icara
    -0.07
    ī¬
    -0.07
    ä¸İéĶĢåĶ®
    -0.07
    æĸĩåĵ²
    -0.07
    POSITIVE LOGITS
    æľįåĬ¡ä¿Ŀéļľ
    0.07
    åħ¬å¼ı
    0.07
    éĢ¼è¿ij
    0.07
    è¿ijä¼¼
    0.07
     approximation
    0.07
    æľ
    0.07
     approximate
    0.07
    æĮĩæķ°
    0.07
     Approx
    0.06
    à¹Ģà¸Ľà¸¥à¹Īา
    0.06
    Activations Density 0.002%

    No Known Activations