© 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. 29454
    Prev
    Next
    INDEX
    Explanations

    including followed by examples

    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
     either
    -0.09
    Either
    -0.08
     либо
    -0.08
     invece
    -0.08
    either
    -0.08
    è¦ģä¹Ī
    -0.08
     anyway
    -0.08
     Either
    -0.07
     EITHER
    -0.07
     anyways
    -0.07
    POSITIVE LOGITS
    à¸Ńยà¹Īาà¸ĩยิà¹Īà¸ĩ
    0.11
     ones
    0.10
    ä¸įéĻIJäºİ
    0.09
    åľ¨åĨħçļĦ
    0.09
    beit
    0.08
     اÛĮÙĨÚ©Ùĩ
    0.08
    åľ¨åĨħ
    0.08
     yours
    0.07
    åĴĮæľĢ
    0.07
    veux
    0.07
    Activations Density 0.091%

    No Known Activations