© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63117
    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
    ipes
    -0.07
     Attr
    -0.07
    emie
    -0.06
    æĻĵ举
    -0.06
    ownt
    -0.06
    ạnh
    -0.06
    她ä¸İ
    -0.06
    ">@
    -0.06
     ÑĦло
    -0.06
     setBackground
    -0.06
    POSITIVE LOGITS
    ä¿IJ
    0.06
    наÑĤ
    0.06
    é±
    0.06
    à¸Īิà¸ķ
    0.06
    utr
    0.06
    éĵ¶å±ijçĹħ
    0.06
    åĺĪ
    0.06
     ways
    0.06
    asseur
    0.06
    rage
    0.06
    Activations Density 0.000%

    No Known Activations