© 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. 29967
    Prev
    Next
    INDEX
    Explanations

    file handling code snippets

    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
    æºī
    -0.08
    heu
    -0.07
     [[]
    -0.07
    积æŀģç»Ħç»ĩ
    -0.07
    以ä¸ĭæľīæľŁå¾ĴåĪij
    -0.07
    æĺ¯åIJ¦èĥ½å¤Ł
    -0.07
    天ä»Ļ
    -0.07
    iza
    -0.07
    ifer
    -0.07
    ürn
    -0.07
    POSITIVE LOGITS
    à¸Ļà¹Į
    0.07
    ogne
    0.07
    osting
    0.07
    oreal
    0.07
    edException
    0.07
    سط
    0.07
    æĿ¥æºIJäºİç½ij绾
    0.07
    .—
    0.06
    伤人
    0.06
    _IMPLEMENT
    0.06
    Activations Density 0.026%

    No Known Activations