© 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. 9427
    Prev
    Next
    INDEX
    Explanations

    time-varying

    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
    è¿ŀéĶģ
    -0.08
    alis
    -0.08
    大马
    -0.07
    ekat
    -0.07
    .std
    -0.07
    åĢ¾åIJij
    -0.07
     Minor
    -0.07
    awah
    -0.07
    æĿ¥ä¸ºå¤§å®¶
    -0.07
    åįģä¹ĿæĿ¡
    -0.07
    POSITIVE LOGITS
     rapidly
    0.08
    changing
    0.08
    å¾Īå¿«çļĦ
    0.08
    åĬ¨èµ·æĿ¥
    0.07
    åıĺåĮĸ
    0.07
    åıĺåĮĸçļĦ
    0.07
    æľŁçļĦ
    0.07
    åij¨åĽ´çݯå¢ĥ
    0.07
    åij¨è¾¹çݯå¢ĥ
    0.07
    /change
    0.07
    Activations Density 0.015%

    No Known Activations