© 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. 34052
    Prev
    Next
    INDEX
    Explanations

    how would

    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
    osso
    -0.08
    第ä¸Ģ大
    -0.07
    çīĪæĿĥä¸İåħį责声æĺİ
    -0.07
    该项
    -0.07
    æŁIJç§įæĦıä¹īä¸Ĭ
    -0.07
    çļĦ缮çļĦ
    -0.07
    esm
    -0.07
    è¿ĿèĢħ
    -0.07
    ä¸Ńç§ij
    -0.07
    rance
    -0.07
    POSITIVE LOGITS
    å¦Ĥä½ķå°Ĩ
    0.07
    ulous
    0.07
    å¦Ĥä½ķçĶ¨
    0.06
    æŁ¥çľĭåħ¨éĥ¨
    0.06
    æݪ
    0.06
    _shapes
    0.06
    ABEL
    0.06
    èIJ½æĪIJ
    0.06
    å¦Ĥä½ķéĢļè¿ĩ
    0.06
    峨
    0.06
    Activations Density 0.102%

    No Known Activations