© 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. 21833
    Prev
    Next
    INDEX
    Explanations

    duality, Famed, drug, .C., asiliximab

    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
    odon
    -0.07
    кипа
    -0.07
    kee
    -0.07
    upp
    -0.07
    unes
    -0.06
     increment
    -0.06
     Increment
    -0.06
    Increment
    -0.06
    èĮ¶æ°´
    -0.06
    åıĮåŁİ
    -0.06
    POSITIVE LOGITS
    leb
    0.08
    ึม
    0.07
    ToLocal
    0.07
    èĪħ
    0.07
     pervasive
    0.07
    æŀķ
    0.07
    çĶ¨æ³ķ
    0.07
    emain
    0.07
    paging
    0.07
     Beau
    0.07
    Activations Density 0.004%

    No Known Activations