© 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. 45289
    Prev
    Next
    INDEX
    Explanations

    mathematical integrals and sums

    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
    çĿ«
    -0.08
    ynos
    -0.07
    hir
    -0.07
    ãĤ¸ãĥ¼
    -0.07
    ä¹ħä¹ĭ
    -0.07
    usat
    -0.07
    _ASCII
    -0.07
     Ont
    -0.07
    ä¹ĭéģ¥
    -0.07
    дзе
    -0.07
    POSITIVE LOGITS
    /rfc
    0.07
    éĿ¢å¯¹éĿ¢
    0.07
    pec
    0.06
    dbl
    0.06
    è°Īèµ·
    0.06
    åħļæĢ»æĶ¯ä¹¦è®°
    0.06
     ${(
    0.06
    ×ķר×Ļ×Ŀ
    0.06
    ially
    0.06
    ìĦ¸
    0.06
    Activations Density 0.004%

    No Known Activations