© 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. 64701
    Prev
    Next
    INDEX
    Explanations

    definition or coined term

    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
    ubl
    -0.09
    anzas
    -0.09
    ابÛĮ
    -0.08
     prestigi
    -0.08
    /generated
    -0.08
    ingend
    -0.08
    åĨį说
    -0.07
    æĶ¶èĹıæľ¬ç«Ļ
    -0.07
     λÏĮγο
    -0.07
     massiv
    -0.07
    POSITIVE LOGITS
    æĺ¯æĮĩåľ¨
    0.10
     coined
    0.10
    æ¦Ĥ念
    0.10
    æĮĩçļĦæĺ¯
    0.10
    顾åIJįæĢĿä¹ī
    0.09
    æĺ¯æĮĩ
    0.08
    çļĦæ¦Ĥ念
    0.08
     concept
    0.08
     refers
    0.08
    åĢŁçĶ¨
    0.07
    Activations Density 0.155%

    No Known Activations