© 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. 8716
    Prev
    Next
    INDEX
    Explanations

    widespread, widely, popular, common

    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
    tür
    -0.09
    æĺ¯ä¸įæĺ¯å¾Ī
    -0.07
    öp
    -0.07
    ủng
    -0.07
     вд
    -0.07
     meticulously
    -0.07
    ä½Ĩåıªè¦ģ
    -0.06
    ä¹ĸ
    -0.06
     ideally
    -0.06
    nik
    -0.06
    POSITIVE LOGITS
    èĢĮä¸Ķæĺ¯
    0.09
    èĢĮä¸Ķåľ¨
    0.08
    ä¸Ķåľ¨
    0.08
    并ä¸Ķåľ¨
    0.08
    ä¸Ķæľī
    0.07
    abet
    0.07
    æľīæĽ´å¤ļçļĦ
    0.07
    ãĥŀãĤ¹
    0.07
    çī¹åĪ«æĺ¯åľ¨
    0.07
    æľī大éĩı
    0.07
    Activations Density 0.006%

    No Known Activations