© 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. 64314
    Prev
    Next
    INDEX
    Explanations

    ground and surface levels

    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
    ç¹¼
    -0.08
    鼶件
    -0.08
    ellation
    -0.08
     Stras
    -0.08
    digest
    -0.08
    Ñħоди
    -0.08
    继
    -0.07
    Ắ
    -0.07
    ewise
    -0.07
    nore
    -0.07
    POSITIVE LOGITS
     terrestrial
    0.09
    åľ°éĿ¢
    0.09
    -ground
    0.09
     ground
    0.09
    åľ°éĿ¢ä¸Ĭ
    0.08
     earth
    0.08
     terrestre
    0.08
    earth
    0.08
    åľ°éĿ¢çļĦ
    0.08
     surface
    0.08
    Activations Density 0.026%

    No Known Activations