© 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. 63874
    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
    anes
    -0.09
    kow
    -0.08
    aned
    -0.08
    ÙĪز
    -0.08
    ancio
    -0.07
    isher
    -0.07
    emm
    -0.07
    æŁ»
    -0.07
    Wake
    -0.07
    社ä¼ļåĮĸ
    -0.07
    POSITIVE LOGITS
    ÏĥÏĦι
    0.07
    ä¸į好äºĨ
    0.07
    ä¸įå®ĮçļĦ
    0.07
    ite
    0.06
    lad
    0.06
    ôn
    0.06
    åħ»æĪIJ
    0.06
    íĥĦ
    0.06
    мп
    0.06
    uille
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.