© 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. 11760
    Prev
    Next
    INDEX
    Explanations

    inclusion over privatization

    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
    acruz
    -0.08
    ×ķר×ķת
    -0.07
    obod
    -0.07
    indik
    -0.07
    æŁ¥æ¼ı
    -0.07
    brig
    -0.07
    دÙĪز
    -0.07
    agu
    -0.07
    ×ķר×Ļ×Ŀ
    -0.07
    akil
    -0.07
    POSITIVE LOGITS
    гол
    0.06
    icio
    0.06
    -API
    0.06
    -Version
    0.06
    åºľ
    0.06
    ivers
    0.06
    dok
    0.06
    ÏĦÏģÏĮ
    0.06
    าม
    0.06
    sembler
    0.06
    Activations Density 0.485%

    No Known Activations