© 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. 18743
    Prev
    Next
    INDEX
    Explanations

    heat diffusion equations

    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
    raub
    -0.08
    guas
    -0.08
     Spurs
    -0.08
    å¬Ľ
    -0.08
    ignon
    -0.08
    ereien
    -0.08
    ä¸ŃèģĶ
    -0.08
    /fontawesome
    -0.07
    .edu
    -0.07
    DialogTitle
    -0.07
    POSITIVE LOGITS
     diffusion
    0.09
    æī©æķ£
    0.08
     heat
    0.08
     Fourier
    0.08
    heat
    0.07
     поÑģÑĤанов
    0.07
     Saint
    0.07
     time
    0.07
     Heat
    0.07
    oven
    0.07
    Activations Density 0.018%

    No Known Activations