© 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. 11422
    Prev
    Next
    INDEX
    Explanations

    autoimmune diseases

    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
    erot
    -0.08
    ullet
    -0.08
     ÑģоÑĥ
    -0.07
    å¢ŀéķ¿çĤ¹
    -0.07
     compression
    -0.07
    çļĦè¡Į
    -0.07
    crimin
    -0.07
    compressed
    -0.07
    нÑİ
    -0.07
    opus
    -0.07
    POSITIVE LOGITS
    èĩªèº«åħįçĸ«
    0.11
     autoimmune
    0.09
    èĨľ
    0.08
    æ¼Ĩ
    0.08
    éĿ¶
    0.08
    æĬĹä½ĵ
    0.08
    人社
    0.07
     antig
    0.07
    inkel
    0.07
    wehr
    0.07
    Activations Density 0.087%

    No Known Activations