© 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. 31548
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by a capitalized word

    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
    اÙĤرأ
    -0.07
    fek
    -0.07
    ecke
    -0.07
    öker
    -0.07
    ungk
    -0.07
    éĤ£åIJį
    -0.06
    çļĦ人士
    -0.06
    iman
    -0.06
     Kais
    -0.06
    ¨
    -0.06
    POSITIVE LOGITS
    ضÙħ
    0.07
    duce
    0.07
    водим
    0.07
    вÑĸÑĢ
    0.07
    atriz
    0.06
    able
    0.06
    ł
    0.06
     proceder
    0.06
    au
    0.06
    ÑģÑĤÑĢом
    0.06
    Activations Density 0.005%

    No Known Activations