© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29764
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving numbers and operators

    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
    Ĥ¬
    -0.08
    åŃ¦å¥½
    -0.07
    Ñģл
    -0.07
    ÃįT
    -0.07
    æķ°éĩı为
    -0.07
    lix
    -0.07
    LIK
    -0.07
    bject
    -0.07
    åħīæĺİçļĦ
    -0.06
    upert
    -0.06
    POSITIVE LOGITS
    aby
    0.08
    abra
    0.07
    uca
    0.07
    天æĪIJ
    0.07
    klı
    0.06
    essen
    0.06
    à¥Ĥस
    0.06
    ensos
    0.06
    âm
    0.06
    åIJ¦è®¤
    0.06
    Activations Density 0.001%

    No Known Activations