© 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. 30571
    Prev
    Next
    INDEX
    Explanations

    regarding education, concerning, regarding

    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
    ANIA
    -0.07
    è¡Ļ
    -0.07
    inkel
    -0.07
    szy
    -0.07
    ض
    -0.07
    ì§ĦíĿ¥
    -0.07
    ZIA
    -0.07
    .googlecode
    -0.07
    nga
    -0.06
    бии
    -0.06
    POSITIVE LOGITS
    åħ³äºİ
    0.11
    à¸Ķà¹īาà¸Ļà¸ģาร
    0.10
     regarding
    0.09
    à¹Ģรืà¹Īà¸Ńà¸ĩà¸ģาร
    0.08
    æľīåħ³äºİ
    0.08
    à¹Ģà¸ģีà¹Īยวà¸ģัà¸ļà¸ģาร
    0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    0.08
     Regarding
    0.08
     concerning
    0.08
    æĽ´å¤ļåħ³äºİ
    0.08
    Activations Density 1.283%

    No Known Activations