© 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. 38131
    Prev
    Next
    INDEX
    Explanations

    code structure initialization

    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
    éĹª
    -0.07
    éĽĨä¸Ń
    -0.07
    å°ijçļĦ
    -0.07
    èĭ«
    -0.07
    ä¸ĢéĹª
    -0.07
    igmat
    -0.07
     Bany
    -0.06
    太å¤ļ
    -0.06
     ÄijỼi
    -0.06
    iso
    -0.06
    POSITIVE LOGITS
    ufer
    0.08
    chst
    0.07
    ghi
    0.07
    äºijå³°
    0.07
    OnInit
    0.07
    οÏįμε
    0.07
    ãĥģãĥ¥ãĥ¼
    0.07
    thu
    0.07
    zinho
    0.07
     à¦ķরà§ĩ
    0.07
    Activations Density 0.024%

    No Known Activations