© 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. 58329
    Prev
    Next
    INDEX
    Explanations

    punctuation and subsequent words

    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
    âĨ³
    -0.06
    社ä¼ļåĴĮ
    -0.06
    _h
    -0.06
    aris
    -0.06
    инÑĥ
    -0.06
    ilon
    -0.06
    rap
    -0.06
    åĿ¡
    -0.06
     kej
    -0.06
    лиÑĨ
    -0.06
    POSITIVE LOGITS
    ergy
    0.08
    stur
    0.08
    .scheme
    0.08
    ioned
    0.07
    bito
    0.07
    _locations
    0.07
    à®Łà¯Ī
    0.07
    eryl
    0.07
    [][]
    0.07
     inout
    0.07
    Activations Density 0.010%

    No Known Activations