© 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. 32417
    Prev
    Next
    INDEX
    Explanations

    statistical and physical measurements

    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
    heb
    -0.08
    alto
    -0.07
    rollo
    -0.07
    atang
    -0.07
     Lans
    -0.07
    atto
    -0.07
    奢
    -0.07
    bogen
    -0.07
    é½IJé½IJ
    -0.06
    æľīç¦ı
    -0.06
    POSITIVE LOGITS
    度éĩı
    0.07
    åľ¨æŁIJ
    0.07
    aira
    0.07
    /path
    0.07
    äºĪ
    0.07
    idity
    0.07
    mira
    0.07
    ä¸īçķĮ
    0.06
    _squared
    0.06
    anggung
    0.06
    Activations Density 0.013%

    No Known Activations