© 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. 11482
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
    ingos
    -0.07
    ä¾
    -0.07
    ç«ĭå¤ı
    -0.07
    eson
    -0.06
    ingo
    -0.06
    èĪħ
    -0.06
    èĴ
    -0.06
    èģĮä¸ļåѦéĻ¢
    -0.06
    onsin
    -0.06
    nex
    -0.06
    POSITIVE LOGITS
     Conversely
    0.10
    ä½ĨåIJĮæŶ
    0.10
    åıįä¹ĭ
    0.09
     indirectly
    0.08
    缸åıį
    0.08
     convers
    0.07
    æķĪæŀľæĽ´å¥½
    0.07
    åı¦ä¸Ģæĸ¹éĿ¢
    0.07
     haus
    0.07
    æķĪæŀľ
    0.07
    Activations Density 0.026%

    No Known Activations