© 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. 50756
    Prev
    Next
    INDEX
    Explanations

    medical conditions and rehabilitation

    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
    .ms
    -0.08
    æľĢåIJİ
    -0.07
    oby
    -0.07
     Urbano
    -0.07
    olog
    -0.07
     last
    -0.07
    å·¥ä½ľä¸ļ
    -0.07
    ries
    -0.07
    Getty
    -0.06
    ç®Ĺ
    -0.06
    POSITIVE LOGITS
    edom
    0.09
    ª½
    0.09
    ìĦľ
    0.08
    ä¸įæĹ©
    0.07
    æĵĤ
    0.07
    аниÑĨ
    0.07
    Įĵ
    0.07
     '(
    0.07
     asal
    0.07
     lej
    0.07
    Activations Density 0.001%

    No Known Activations