© 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. 49447
    Prev
    Next
    INDEX
    Explanations

    cases and appeals

    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
    дÑĥк
    -0.08
    تر
    -0.07
    AGR
    -0.07
    менÑĤиÑĢов
    -0.06
    oyo
    -0.06
    yat
    -0.06
    ollar
    -0.06
    åĩĮéľĦ
    -0.06
     tril
    -0.06
    гли
    -0.06
    POSITIVE LOGITS
    beste
    0.08
    æĪijåij¢
    0.08
     Mendes
    0.08
    cona
    0.07
     concerning
    0.07
    èĬĬ
    0.07
    æ´»åĬ¨å¼Ģå±ķ
    0.07
    ÏĥÏĥ
    0.07
    assets
    0.07
    _INSTANCE
    0.07
    Activations Density 0.003%

    No Known Activations