© 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. 9363
    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
    otlin
    -0.07
    ÏĦÏģι
    -0.07
    زاÙħ
    -0.07
    odiac
    -0.07
    trash
    -0.07
     trá»ĭ
    -0.07
    ä¿ĿæĮģçĿĢ
    -0.06
    åĽ´ç»ķçĿĢ
    -0.06
    ãģ¾ãģĦ
    -0.06
    yar
    -0.06
    POSITIVE LOGITS
    å¿Ĺæĺİ
    0.08
    engt
    0.07
    warf
    0.07
    erken
    0.07
    åĩłæ¬¾
    0.07
    indr
    0.07
    à¤ĸा
    0.07
    istra
    0.07
     enclosed
    0.07
    åĬŁäºİ
    0.07
    Activations Density 0.000%

    No Known Activations