© 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. 26158
    Prev
    Next
    INDEX
    Explanations

    java.util imports

    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
    ightly
    -0.07
    Ùıب
    -0.07
    ushima
    -0.06
    igh
    -0.06
     '</
    -0.06
    çİĩåľ¨
    -0.06
    aramente
    -0.06
    ight
    -0.06
    ovid
    -0.06
    ighth
    -0.06
    POSITIVE LOGITS
    trin
    0.07
    åĽłä¸ºä½ł
    0.07
    Comm
    0.07
    ä½Ĩä¹Ł
    0.07
    reet
    0.07
    ompat
    0.07
    åĽłæĤ¨çļĦ
    0.07
     import
    0.07
    åIJĮä»ģ
    0.07
    åĥıæĪij
    0.07
    Activations Density 0.077%

    No Known Activations