© 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. 17174
    Prev
    Next
    INDEX
    Explanations

    but, however, subsequently, not

    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
    ä¸įèµ°
    -0.07
    ä¸įå°½
    -0.07
    Destroyed
    -0.07
    åľ°å¤´
    -0.07
    ä¸ĥæĺŁ
    -0.07
    æĹ¥çĶŁ
    -0.07
    æĮĩ导åijĺ
    -0.07
    éĴ§
    -0.07
    egt
    -0.07
     Oli
    -0.06
    POSITIVE LOGITS
    她åį´
    0.07
    åĽŀæĿ¥åIJİ
    0.07
    åı¦ä¸Ģç§į
    0.07
    éģ½
    0.07
    ãģ¾ãģĽãĤĵãģĭ
    0.07
    lient
    0.07
    erate
    0.07
    à¹ĭ
    0.07
    thouse
    0.07
     kiá»ģu
    0.07
    Activations Density 0.018%

    No Known Activations