© 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. 2090
    Prev
    Next
    INDEX
    Explanations

    version information and 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
    immel
    -0.08
    贯穿
    -0.07
    åı¸
    -0.06
    antd
    -0.06
     wider
    -0.06
     paraph
    -0.06
    æĽ´ä¸įæĺ¯
    -0.06
    indh
    -0.06
     conc
    -0.06
    .pre
    -0.06
    POSITIVE LOGITS
    天ä¹ĭ
    0.09
    èĴ¸èĴ¸
    0.08
    à¹Ģà¸Ķิม
    0.08
     interni
    0.08
    空éĹ´çļĦ
    0.08
    åѦéĩij
    0.08
    ebes
    0.08
    à¹ģà¸Īà¹īà¸ĩ
    0.08
    .orig
    0.08
    /internal
    0.08
    Activations Density 0.069%

    No Known Activations