© 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. 3729
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    çļĦè¿ĻäºĽ
    -0.08
    erci
    -0.07
    allery
    -0.07
    åı¦è¡ĮéĢļçŁ¥
    -0.07
    æİ¥
    -0.07
    orno
    -0.07
    ultos
    -0.07
    ä¹Łä¸º
    -0.07
    ä¹Łæĺ¯å¾Ī
    -0.07
    adura
    -0.07
    POSITIVE LOGITS
    èĪĬ
    0.07
    iget
    0.07
    çľĭä¼¼
    0.07
    arent
    0.07
    京åħ¬ç½ijå®īå¤ĩ
    0.07
    ByID
    0.07
    åį³éĢĿ
    0.06
    åĽ½æ°ij
    0.06
    à¹Ģà¸Ħรืà¸Ń
    0.06
    åį´åĽłä¸º
    0.06
    Activations Density 0.001%

    No Known Activations