© 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. 18084
    Prev
    Next
    INDEX
    Explanations

    encyclopedia, university, abstract, publication, Washington

    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
    èĨľçĤİ
    -0.07
    ä¸įåIJĮæŶ
    -0.07
    виÑģ
    -0.07
    uhu
    -0.07
    omba
    -0.07
     Demp
    -0.07
    å°±æĭ¿
    -0.06
    èĥĮçĹĽ
    -0.06
    èµ·
    -0.06
    ANI
    -0.06
    POSITIVE LOGITS
     aka
    0.09
    "|
    0.07
    (..
    0.07
     âĢİ
    0.06
    ashes
    0.06
     -
    0.06
    ãĥĿãĤ¹ãĥĪ
    0.06
    ovid
    0.06
    OMP
    0.06
     |
    0.06
    Activations Density 0.242%

    No Known Activations