© 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. 63159
    Prev
    Next
    INDEX
    Explanations

    warped product, HNN extension, Nichols algebras, CoordinatorLayout

    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
    itage
    -0.08
    èĤīçľ¼
    -0.08
    bili
    -0.08
    éĻ¤äºĨè¦ģ
    -0.07
    ä¸Īéĩı
    -0.07
    åĬ©æķĻ
    -0.07
    è¡¡éĩı
    -0.07
    idian
    -0.07
    idel
    -0.07
    arest
    -0.07
    POSITIVE LOGITS
    ly
    0.08
     rotational
    0.07
    ÑĢоÑĤ
    0.07
    æĬĬæı¡å¥½
    0.07
    æĭĽèĤ¡
    0.07
    èģ
    0.06
    ÛĮÙĩ
    0.06
    /non
    0.06
    _ALIGNMENT
    0.06
    ely
    0.06
    Activations Density 0.002%

    No Known Activations