© 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. 16726
    Prev
    Next
    INDEX
    Explanations

    one at a time

    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
    æłijä¸Ģ
    -0.08
    æĪIJ为ä¸ĢåIJį
    -0.08
    ä¸ĢæıIJ
    -0.08
    arged
    -0.08
    iteli
    -0.08
    ë³ij
    -0.07
     altogether
    -0.07
    pras
    -0.07
    _charset
    -0.07
    alle
    -0.07
    POSITIVE LOGITS
    ë§Īëĭ¤
    0.09
     từng
    0.09
    (each
    0.08
    ä¾Ŀ次
    0.08
    ìĶ©
    0.08
    ãģĶãģ¨ãģ«
    0.08
    ãĢħãģ®
    0.08
    ãĢħãģ«
    0.08
    åĪĨæĺİ
    0.08
     individually
    0.08
    Activations Density 0.047%

    No Known Activations