© 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. 61805
    Prev
    Next
    INDEX
    Explanations

    dimer/oligomer/polymer formation

    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
    ä¸īéŨ
    -0.08
    igital
    -0.07
    -0.06
    åİĨ
    -0.06
    èİ«åıĬ
    -0.06
    clock
    -0.06
    नà¥Ģ
    -0.06
     thuần
    -0.06
    -0.06
    ä¸ĢåĪĢ
    -0.06
    POSITIVE LOGITS
     formation
    0.12
     halinde
    0.12
    /group
    0.10
    å½¢æĪIJ
    0.10
    sembles
    0.09
     formations
    0.09
     formed
    0.09
    æĬ±åĽ¢
    0.09
    formation
    0.09
    åľ¨ä¸Ģèµ·çļĦ
    0.09
    Activations Density 0.046%

    No Known Activations