© 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. 24442
    Prev
    Next
    INDEX
    Explanations

    quotation marks and 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
    ities
    -0.06
     "
    -0.06
    ãģĹãĤĤ
    -0.06
    åĪ°ä¸Ģ个
    -0.06
    æł¹æį®åľ°
    -0.06
    zeÅĽ
    -0.06
    elj
    -0.06
    оÑĢо
    -0.06
     '
    -0.06
    åĪ°ä¸ŃåĽ½
    -0.06
    POSITIVE LOGITS
    cop
    0.09
    cian
    0.08
    +)/
    0.07
    stoff
    0.07
    wig
    0.07
    ãĢįãĢģãĢĮ
    0.07
    åŃĹ
    0.07
    acruz
    0.07
    phas
    0.07
     {}\
    0.07
    Activations Density 0.003%

    No Known Activations