© 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. 48432
    Prev
    Next
    INDEX
    Explanations

    formula components and variables

    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
    ÙĥÙIJ
    -0.07
    åħ»
    -0.07
     Freeze
    -0.07
    ajem
    -0.07
    åĨħ容æıIJä¾Ľæĸ¹
    -0.07
    /lg
    -0.07
     충
    -0.07
    INGER
    -0.07
    é¤Ĭ
    -0.07
    лиÑĨ
    -0.07
    POSITIVE LOGITS
     denominator
    0.10
    为éļ¾
    0.08
     denomin
    0.07
    襯
    0.07
    ä¼´å¥ı
    0.07
    istos
    0.07
    fac
    0.07
    衬æīĺ
    0.07
    onne
    0.07
    ilson
    0.07
    Activations Density 0.014%

    No Known Activations