© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21687
    Prev
    Next
    INDEX
    Explanations

    collagen and fibers

    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
    é£Ł
    -0.06
    å¼ĢåĪ°
    -0.06
    æĵįä½ľ
    -0.06
    -oper
    -0.06
     taped
    -0.06
    /token
    -0.06
     disen
    -0.06
    ära
    -0.06
    容
    -0.06
     ëıĻìŀij
    -0.06
    POSITIVE LOGITS
     collagen
    0.13
    èĥ¶åİŁ
    0.11
    ä¿®å¤į
    0.10
     Collagen
    0.10
    èĥ¶åİŁèĽĭçĻ½
    0.10
     fibers
    0.10
    修復
    0.09
    elas
    0.09
     sợi
    0.09
     волок
    0.09
    Activations Density 0.120%

    No Known Activations