© 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. 56321
    Prev
    Next
    INDEX
    Explanations

    i am implementing code

    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
    æľĶ
    -0.07
    unnan
    -0.06
    bole
    -0.06
    adays
    -0.06
    otechn
    -0.06
    tek
    -0.06
    ×ķ×ŀ
    -0.06
    _transient
    -0.06
    å¤ļå¾Ĺ
    -0.06
    鼨ä¼ŀ
    -0.06
    POSITIVE LOGITS
    代çłģå¦Ĥä¸ĭ
    0.09
    ä¹Łè¦ģ注æĦı
    0.09
    对åIJĦ
    0.09
    åĩĨå¤ĩ好äºĨåIJĹ
    0.08
    tia
    0.08
    avent
    0.08
    etton
    0.08
    leos
    0.08
     crimen
    0.08
     Pruitt
    0.07
    Activations Density 0.004%

    No Known Activations