© 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. 18876
    Prev
    Next
    INDEX
    Explanations

    Ginzburg-Landau

    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
    çºı
    -0.07
     nerves
    -0.07
    å¾Ĵæīĭ
    -0.07
    西é¤IJ
    -0.07
    ç©¿åŃĶ
    -0.07
    ä»Ģä¹Īåľ°æĸ¹
    -0.07
    .wrap
    -0.06
     Myth
    -0.06
    kül
    -0.06
    ocities
    -0.06
    POSITIVE LOGITS
    lobs
    0.08
     Fey
    0.07
    egel
    0.07
    UTO
    0.07
    unst
    0.07
    顶ä¸Ĭ
    0.07
    agam
    0.07
    agung
    0.07
    ubic
    0.07
     catast
    0.07
    Activations Density 0.006%

    No Known Activations