© 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. 63212
    Prev
    Next
    INDEX
    Explanations

    i=1 equation numbers

    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
    pdo
    -0.08
    νομ
    -0.08
    -twitter
    -0.07
    inya
    -0.07
    _nd
    -0.07
    bau
    -0.07
    -calendar
    -0.07
    iliz
    -0.07
    -refresh
    -0.07
    ixel
    -0.07
    POSITIVE LOGITS
    æĺ¯ç¬¬ä¸Ģ
    0.07
    åĴĮ第äºĮ
    0.07
    ä¸ĢçıŃ
    0.06
    第äºĮ次
    0.06
    0.06
    åľ¨ç¬¬ä¸Ģ
    0.06
     leg
    0.06
    лиÑĤе
    0.06
    çļĦ第ä¸Ģ
    0.06
    ë¶ĢíĦ°
    0.06
    Activations Density 0.044%

    No Known Activations