© 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. 46626
    Prev
    Next
    INDEX
    Explanations

    squared, square, products

    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
    лон
    -0.08
    ATRIX
    -0.08
    abox
    -0.08
    _MAY
    -0.08
     trik
    -0.08
    ланд
    -0.08
    crypt
    -0.07
    çİĦå¾·
    -0.07
     Podesta
    -0.07
    å§Ĩæĸ¯
    -0.07
    POSITIVE LOGITS
    涧
    0.07
    ief
    0.07
    rale
    0.06
    糯
    0.06
    容
    0.06
    elda
    0.06
    å¿«ä¹IJ
    0.06
    lips
    0.06
    éĺģ
    0.06
    åıĸæļĸ
    0.06
    Activations Density 0.003%

    No Known Activations