© 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. 63174
    Prev
    Next
    INDEX
    Explanations

    Tribe of Dreamers

    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
    avers
    -0.07
    èł
    -0.06
    pon
    -0.06
     ÐĿижний
    -0.06
    conscious
    -0.06
    rani
    -0.06
     دارÛĮÙħ
    -0.06
    åĸľ
    -0.06
     sourceMapping
    -0.06
    atoire
    -0.06
    POSITIVE LOGITS
    æł©æł©
    0.07
    orong
    0.07
     rá
    0.07
    ikken
    0.07
    翱
    0.07
    æī¬æī¬
    0.07
     اÙĦرا
    0.07
    dene
    0.07
    人称
    0.06
    è¿ĺä¸įæĺ¯
    0.06
    Activations Density 0.038%

    No Known Activations