© 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. 27400
    Prev
    Next
    INDEX
    Explanations

    medical journal citations

    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
    è®
    -0.07
    åѤ
    -0.07
     pär
    -0.07
    æ³ĵ
    -0.07
    èµ°
    -0.06
    aidu
    -0.06
    ®
    -0.06
    åħ«ä¹Ŀ
    -0.06
    uset
    -0.06
    åĢį
    -0.06
    POSITIVE LOGITS
    urst
    0.08
    äºĮä¸ĸ
    0.07
    styleType
    0.07
    èĸĦçļĦ
    0.07
    biz
    0.07
    bish
    0.07
    Å¡t
    0.07
     II
    0.07
    II
    0.07
    -II
    0.07
    Activations Density 0.274%

    No Known Activations