© 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. 44023
    Prev
    Next
    INDEX
    Explanations

    activities and data

    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
    pera
    -0.08
    /mL
    -0.08
    ÄĽn
    -0.08
    (Print
    -0.08
    è¦ģç»ı常
    -0.07
    OfYear
    -0.07
    å¥½å£°éŁ³
    -0.07
    åįļä¼ļ
    -0.07
    ä¸ĭè½½æĬ¥åijĬ
    -0.07
    Stencil
    -0.07
    POSITIVE LOGITS
    ä¹±
    0.08
     riêng
    0.07
    大åIJĮ
    0.07
    ẫn
    0.07
    anse
    0.07
    icon
    0.06
    refs
    0.06
    -style
    0.06
    ãģĿ
    0.06
     Independence
    0.06
    Activations Density 0.282%

    No Known Activations