© 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. 21649
    Prev
    Next
    INDEX
    Explanations

    Monthly Archives

    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
    iek
    -0.08
    æĪIJçĨŁ
    -0.07
    çݯå¢ĥä¸Ń
    -0.06
    æĥħåĨµä¸ĭ
    -0.06
    pers
    -0.06
    empo
    -0.06
    æĪIJçĨŁçļĦ
    -0.06
    totalCount
    -0.06
    ÙħاÙĨ
    -0.06
    éĢļ常
    -0.06
    POSITIVE LOGITS
     finally
    0.08
     despe
    0.08
     enfin
    0.08
    æ£ĢæŁ¥ç»ĵæŀľ
    0.08
    æIJŃä¸Ĭ
    0.07
    继èĢĮ
    0.07
     finalmente
    0.07
    finally
    0.07
    å¾Ĺåĩºç»ĵ论
    0.07
    èĤ¡ä¸ľåıĬ
    0.07
    Activations Density 0.013%

    No Known Activations