© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16346
    Prev
    Next
    INDEX
    Explanations

    medical and scientific abstracts

    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
    åĬªåĬĽå®ŀçİ°
    -0.07
    ä»Ģä¹Īæĺ¯
    -0.07
    éĢļè¿ĩåIJĦç§į
    -0.07
    BaseUrl
    -0.07
     await
    -0.06
    ä¸įè¦ģçĶ¨
    -0.06
    说åĩºäºĨ
    -0.06
    inger
    -0.06
    IJ
    -0.06
    å®īåIJī
    -0.06
    POSITIVE LOGITS
    ixo
    0.08
    ledo
    0.07
    aeda
    0.07
    -License
    0.07
    emd
    0.07
    åīĽå¥½
    0.07
    semblies
    0.07
    æŃ£å¥½
    0.07
    etheless
    0.07
    emos
    0.07
    Activations Density 0.001%

    No Known Activations