© 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. 45855
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with `log` and `sqrt`

    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
    lau
    -0.07
    erbe
    -0.07
    æħµ
    -0.07
    Ú©Ø´
    -0.07
    ä¸įè¾ŀ
    -0.07
    èªī
    -0.07
    代ä¹ĭ
    -0.07
    Argent
    -0.06
    agus
    -0.06
    æ¸Ĭ
    -0.06
    POSITIVE LOGITS
    çī¹çĤ¹æĺ¯
    0.08
    éģĵåı£
    0.07
    anz
    0.07
    äºĮæĺ¯
    0.07
    blick
    0.06
    ä»·æł¼æĺ¯
    0.06
    éĥ¨åĪĨæĺ¯
    0.06
     Randolph
    0.06
     disag
    0.06
    é¾Ļä¹ĭ
    0.06
    Activations Density 0.013%

    No Known Activations