© 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. 19970
    Prev
    Next
    INDEX
    Explanations

    roots and mathematical expressions

    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
    rogram
    -0.07
    uper
    -0.07
     manti
    -0.07
    èĩªçĶ±æ´»åĬ¨
    -0.07
    upun
    -0.07
    blad
    -0.07
    uxtap
    -0.07
    æĹ¥ä¸Ĭ
    -0.07
    agos
    -0.07
    é¼ĵ
    -0.07
    POSITIVE LOGITS
     Corr
    0.06
    è²¢
    0.06
     resa
    0.06
    åĪĿä¸ī
    0.06
    è´¡
    0.06
    odox
    0.06
    æĢ§èĥ½
    0.06
    éĹ®é¢ĺ解åĨ³
    0.06
     crave
    0.06
    alloc
    0.06
    Activations Density 0.002%

    No Known Activations