© 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. 57471
    Prev
    Next
    INDEX
    Explanations

    question words that start phrases

    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
    å¦ĤæŃĮ
    -0.08
    jak
    -0.08
    moc
    -0.07
    ä¹Łæĺ¯å¦ĤæѤ
    -0.07
    ĽĦ
    -0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.07
    å¦Ĥä½ķåģļ
    -0.07
    رÙĬÙħ
    -0.07
     Everywhere
    -0.07
    æĹłéĿŀ
    -0.07
    POSITIVE LOGITS
    llib
    0.07
    \u
    0.07
    atables
    0.07
    />\
    0.06
    \n
    0.06
    acob
    0.06
    âĢĮ
    0.06
    Ñģловно
    0.06
    次åħĥ
    0.06
    \xe
    0.06
    Activations Density 0.261%

    No Known Activations