© 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. 7646
    Prev
    Next
    INDEX
    Explanations

    familial Mediterranean fever

    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
    Ł
    -0.07
    ulare
    -0.07
    座
    -0.07
    /xhtml
    -0.07
    館
    -0.07
    ç²Ĺ
    -0.07
    åĵī
    -0.07
    座çļĦ
    -0.07
    Sir
    -0.06
     sir
    -0.06
    POSITIVE LOGITS
    ä¾®
    0.08
    缣
    0.08
    innen
    0.07
    elper
    0.07
    å°ıå±±
    0.07
    åĽłä¸ºåħ¶
    0.07
    IPH
    0.07
    éron
    0.07
     <<-
    0.07
    plast
    0.07
    Activations Density 0.002%

    No Known Activations