© 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. 11888
    Prev
    Next
    INDEX
    Explanations

    open source software

    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
    новÑĮ
    -0.08
    unami
    -0.08
    ãĤ¡
    -0.08
    ually
    -0.08
    ç»Ŀ伦
    -0.07
    oodoo
    -0.07
    ãģ£ãģıãĤĬ
    -0.07
    Ĺ
    -0.07
    irk
    -0.07
    çİĭèı²
    -0.07
    POSITIVE LOGITS
    ness
    0.12
    -ended
    0.12
    ended
    0.08
    /close
    0.08
    esame
    0.08
    ledged
    0.08
    liness
    0.08
    wards
    0.08
    à¸Ķà¹Į
    0.07
    /open
    0.07
    Activations Density 0.104%

    No Known Activations