© 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. 50628
    Prev
    Next
    INDEX
    Explanations

    table or folder names

    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
    ãĤĴä¸ĭ
    -0.07
     ÐĵлÑĥ
    -0.07
    èİĺ
    -0.07
    åĪª
    -0.07
     Heads
    -0.07
     mono
    -0.06
    itness
    -0.06
    æ½¼
    -0.06
    ych
    -0.06
    ulfilled
    -0.06
    POSITIVE LOGITS
    ä»»æĦı
    0.10
     arbitrary
    0.10
    åı¯ä»¥æł¹æį®
    0.10
    åı¯æł¹æį®
    0.09
    éļıæĦıçļĦ
    0.09
     randomly
    0.09
    éļıæĦı
    0.09
    éļıæľº
    0.09
    æĮĩå®ļ
    0.09
    éļı便
    0.09
    Activations Density 0.361%

    No Known Activations