© 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. 19177
    Prev
    Next
    INDEX
    Explanations

    materials and structures

    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
    ấu
    -0.07
    éĿŀåĩ¡
    -0.07
     Richt
    -0.07
    ä¹ĭèĬ±
    -0.07
    -themed
    -0.07
    avn
    -0.07
    .fm
    -0.07
    lify
    -0.06
    -minded
    -0.06
     ìľłíĺķìĿĺ
    -0.06
    POSITIVE LOGITS
    amentals
    0.07
    ÑĤки
    0.07
    (AT
    0.07
    izes
    0.07
    izada
    0.07
    ë°į
    0.07
    å£Į
    0.07
    prd
    0.07
    iasco
    0.07
    cules
    0.07
    Activations Density 0.378%

    No Known Activations