© 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. 14682
    Prev
    Next
    INDEX
    Explanations

    periods and commas followed by words

    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
    getInstance
    -0.08
     Bambini
    -0.08
    åĪ«åIJį
    -0.08
    berge
    -0.07
    ernote
    -0.07
     bru
    -0.07
    Tunes
    -0.07
    othing
    -0.07
    ceo
    -0.07
    texte
    -0.07
    POSITIVE LOGITS
    zem
    0.07
     matter
    0.07
    Ùijا
    0.06
    elters
    0.06
    ('.'
    0.06
     Pruitt
    0.06
    丰å¯Įå¤ļ彩çļĦ
    0.06
    may
    0.06
     matters
    0.06
    ÙİÙijا
    0.06
    Activations Density 0.029%

    No Known Activations