© 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. 46864
    Prev
    Next
    INDEX
    Explanations

    imbalanced, monolithic, underweight, unattended, in-proc, out-of-proc, contactless, unsorted, XDR, degenerate

    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
    лоÑĤо
    -0.07
    enschaft
    -0.07
    iedi
    -0.07
    çī
    -0.06
    ometri
    -0.06
     neuest
    -0.06
    à¥įन
    -0.06
    ологи
    -0.06
    ืà¸Ńà¸ģ
    -0.06
    çĭ¬ä¸ĢæĹłäºĮ
    -0.06
    POSITIVE LOGITS
    /non
    0.08
    åģ¥
    0.08
    ErrorException
    0.08
    (er
    0.08
    uous
    0.08
    ä¸ĢçĤ¹çļĦ
    0.07
    ole
    0.07
    çīĪ车åŀĭ
    0.07
    -bodied
    0.07
    AsyncResult
    0.07
    Activations Density 0.218%

    No Known Activations