© 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. 11840
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and code

    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
    åijµåijµ
    -0.07
    hum
    -0.07
    æij¸æij¸
    -0.07
    ÙĬاتÙĩ
    -0.06
    ENDOR
    -0.06
    nces
    -0.06
    èĦļè·Ł
    -0.06
    hofer
    -0.06
    en
    -0.06
    enzi
    -0.06
    POSITIVE LOGITS
    ´
    0.08
    ırı
    0.07
    çĨł
    0.07
     Kini
    0.07
    à¹Ģลยà¹Į
    0.07
    å¿ĹæĦ¿å¡«æĬ¥
    0.07
    agé
    0.07
    ucc
    0.07
    uplic
    0.06
    æĢ¨
    0.06
    Activations Density 0.004%

    No Known Activations