© 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. 65094
    Prev
    Next
    INDEX
    Explanations

    explaining concepts and their attributes

    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
     alike
    -0.07
    etje
    -0.07
    ilah
    -0.07
     whoever
    -0.07
    rij
    -0.07
     либо
    -0.07
     **.**
    -0.07
     entweder
    -0.07
     inilah
    -0.07
    ä¹ĥèĩ³
    -0.07
    POSITIVE LOGITS
    好åij¢
    0.08
    æĪijåij¢
    0.07
     \"
    0.07
    '?
    0.07
     ghost
    0.07
    åijĥ
    0.06
    çļĦåij¢
    0.06
     versus
    0.06
    ã
    0.06
    à¸ĸ
    0.06
    Activations Density 0.208%

    No Known Activations