© 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. 62175
    Prev
    Next
    INDEX
    Explanations

    torn ACL

    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
    osu
    -0.08
    msp
    -0.08
    ä»ĸçĶļèĩ³
    -0.07
    åĵº
    -0.07
    AGA
    -0.07
    貿
    -0.07
    à¹Ģà¸ĭล
    -0.07
    æ°ĶåĴĮ
    -0.07
    zej
    -0.07
    ä¾ĭå¦Ĥ
    -0.07
    POSITIVE LOGITS
    è¦ģä¹Īæĺ¯
    0.09
    è¦ģä¹Ī
    0.09
     respective
    0.08
    åIJĦèĩª
    0.08
    æĪĸå¤ļæĪĸå°ij
    0.08
     either
    0.08
    约èĢĮåIJĮ
    0.08
    à¸Ĺัà¹īà¸ĩสิà¹īà¸Ļ
    0.07
    either
    0.07
     либо
    0.07
    Activations Density 0.393%

    No Known Activations