© 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. 25282
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    alling
    -0.07
    åīį身
    -0.07
    幡
    -0.07
    ụng
    -0.07
    weg
    -0.07
    éĹ´
    -0.07
    -/
    -0.07
    à°ķ
    -0.06
    nad
    -0.06
    çľģå§Ķ书记
    -0.06
    POSITIVE LOGITS
    (dtype
    0.07
    交åĬŀ
    0.07
    æĪIJç«ĭçļĦ
    0.07
    either
    0.07
     either
    0.07
    ίο
    0.06
    sher
    0.06
     Tut
    0.06
    常人
    0.06
     nhiêu
    0.06
    Activations Density 0.000%

    No Known Activations