© 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. 7964
    Prev
    Next
    INDEX
    Explanations

    code block start `my` return

    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
    úa
    -0.07
     “âĢ¦
    -0.07
     "...
    -0.07
    å¼¥
    -0.06
    å¾®ç¬ijçĿĢ
    -0.06
    åĬ¨
    -0.06
    pit
    -0.06
    ica
    -0.06
    ieder
    -0.06
     Vidal
    -0.06
    POSITIVE LOGITS
    ä¹ĭ士
    0.08
     print
    0.07
    etype
    0.07
    ç½Ĺæĭī
    0.07
    iggers
    0.07
    formatted
    0.07
     [,
    0.07
    æ¶ĪåĮĸçļĦ
    0.07
     Print
    0.07
    ä¹Ŀä¹Ŀ
    0.07
    Activations Density 0.004%

    No Known Activations