© 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. 11326
    Prev
    Next
    INDEX
    Explanations

    Ramanujan sums and Fourier transforms

    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
    rust
    -0.07
     ÑĤÑĢÑĥ
    -0.07
    ç¾Ķ
    -0.07
    obre
    -0.07
     оба
    -0.07
     beide
    -0.07
     altr
    -0.07
    åıĤåĬłå·¥ä½ľ
    -0.07
    obel
    -0.07
    ç«ĭæĸ°
    -0.07
    POSITIVE LOGITS
    isque
    0.08
     Filtering
    0.08
    beck
    0.08
    å²IJ
    0.08
     Fourier
    0.07
     enumerator
    0.07
    ynet
    0.07
     sums
    0.07
     filtering
    0.07
    æ¸ħ宫
    0.07
    Activations Density 0.004%

    No Known Activations