© 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. 40114
    Prev
    Next
    INDEX
    Explanations

    automatic actions and configurations

    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
    cipher
    -0.09
    ocha
    -0.08
    èµĦæĸĻä¸ĭè½½
    -0.08
     {[
    -0.08
    .exports
    -0.08
    utri
    -0.08
    arca
    -0.08
     планÑĥ
    -0.07
    檢è¦ĸ
    -0.07
    æģº
    -0.07
    POSITIVE LOGITS
     automatically
    0.26
    èĩªåĬ¨
    0.25
     automatic
    0.23
     Automatically
    0.21
    èĩªåĭķ
    0.20
     automáticamente
    0.20
     automatisch
    0.20
     авÑĤомаÑĤиÑĩеÑģки
    0.19
    ä¼ļèĩªåĬ¨
    0.19
     automática
    0.19
    Activations Density 0.444%

    No Known Activations