© 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. 34199
    Prev
    Next
    INDEX
    Explanations

    illustration/depiction/equation followed by number

    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
    ingin
    -0.10
    ä¸īæĹł
    -0.07
    ÙĦاء
    -0.07
    æĹłéĹ»
    -0.07
    ebro
    -0.07
    以ä¸ĭåĩłçĤ¹
    -0.07
    ippi
    -0.07
     Articoli
    -0.07
    akse
    -0.07
    èĩªå·±çļĦ人
    -0.07
    POSITIVE LOGITS
    ìĦł
    0.07
    á»ı
    0.06
    æĺ±
    0.06
    æīĭæľºç«¯
    0.06
     Gow
    0.06
    第äºĮ次
    0.06
    REP
    0.06
    èĩ³æѤ
    0.06
    wend
    0.06
    à¹Ģล
    0.06
    Activations Density 0.056%

    No Known Activations