© 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. 14800
    Prev
    Next
    INDEX
    Explanations

    court document filings

    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
    -0.08
    ä¼´
    -0.07
    isci
    -0.06
    ared
    -0.06
    æľ¬ç½ij
    -0.06
    页第
    -0.06
    ured
    -0.06
    å®īæİĴåľ¨
    -0.06
    åıĺæĽ´é¡¹çĽ®
    -0.06
    weed
    -0.06
    POSITIVE LOGITS
     Eag
    0.08
    ниÑĨи
    0.07
    é£İå°ĺ
    0.07
    å¿«çĤ¹
    0.07
    ä¸įå¼ĥ
    0.07
    andia
    0.07
    åĬ¨ä¸įåĬ¨
    0.07
     archive
    0.06
    ازÛĮ
    0.06
    ypi
    0.06
    Activations Density 0.062%

    No Known Activations