© 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. 41721
    Prev
    Next
    INDEX
    Explanations

    numbers followed by commas

    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
    iniz
    -0.07
    ä»»ä½ķ责任
    -0.07
    arca
    -0.07
    ä»Ģä¹ĪéĹ®é¢ĺ
    -0.07
    çļĦä¸Ģé¢Ĺ
    -0.07
    åĵªäºĽéĹ®é¢ĺ
    -0.07
    åĨįæİ¥
    -0.07
    vlo
    -0.07
    头é¢ħ
    -0.07
    缸åħ³æĥħåĨµ
    -0.07
    POSITIVE LOGITS
    æģ¯
    0.08
    éĤij
    0.08
     geh
    0.07
    عÙĪ
    0.07
     undo
    0.07
    è¯ī被åijĬ
    0.07
    æģ¯çļĦ
    0.07
    hia
    0.07
    uhan
    0.07
     одн
    0.07
    Activations Density 0.061%

    No Known Activations