© 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. 32432
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation and calculations

    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
    ï½ŀãĢį
    -0.08
    upun
    -0.08
    /export
    -0.08
    ÏĢαν
    -0.08
    igy
    -0.08
    åIJĪåIJĮæŶ
    -0.07
    =='
    -0.07
    ÏĥÏĦι
    -0.07
     Weeks
    -0.07
    ())[
    -0.07
    POSITIVE LOGITS
    els
    0.06
    æīŃ
    0.06
    iseau
    0.05
     bắp
    0.05
    edReader
    0.05
    дÑĢоб
    0.05
    Ù°
    0.05
     because
    0.05
     neki
    0.05
    以ä¸Ĭ
    0.05
    Activations Density 0.016%

    No Known Activations