© 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. 61633
    Prev
    Next
    INDEX
    Explanations

    citation markers

    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
    uchu
    -0.07
    ØŃÙĬ
    -0.06
    nown
    -0.06
    cona
    -0.06
    akon
    -0.06
    åįİé¾Ļ
    -0.06
    vh
    -0.06
    oad
    -0.06
    çļĦ身å¿ĥ
    -0.06
    丽人
    -0.06
    POSITIVE LOGITS
    æĸ°å¼Ģ
    0.08
    WithType
    0.07
    otch
    0.07
     NHL
    0.07
    Assignable
    0.07
    andle
    0.07
    WithPath
    0.07
    æĿĥ
    0.06
    好æĪIJ绩
    0.06
     Neto
    0.06
    Activations Density 0.164%

    No Known Activations