© 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. 39972
    Prev
    Next
    INDEX
    Explanations

    code completion punctuation

    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
    abal
    -0.08
    pir
    -0.07
    #region
    -0.07
    人æĦı
    -0.07
    até
    -0.07
     dozen
    -0.07
    uler
    -0.07
    ë¦Ħ
    -0.07
    ulp
    -0.07
    ankan
    -0.07
    POSITIVE LOGITS
    !!:
    0.07
    åĢ¼æĺ¯
    0.07
     Liber
    0.07
    ::$_
    0.06
    akers
    0.06
    erschaft
    0.06
    æŃ
    0.06
    代ä¹ĭ
    0.06
    życz
    0.06
    :str
    0.06
    Activations Density 0.162%

    No Known Activations