© 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. 32612
    Prev
    Next
    INDEX
    Explanations

    -1 to 1

    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
    令第
    -0.08
    onet
    -0.07
    åħīåĴĮ
    -0.06
    nier
    -0.06
     ÙħرØŃ
    -0.06
    nior
    -0.06
    äger
    -0.06
    اصر
    -0.06
    alt
    -0.06
    ynos
    -0.06
    POSITIVE LOGITS
    ç©
    0.08
    Õµ
    0.08
    ä¸Ĭä¸ĭ
    0.08
    abis
    0.08
     लà¥ĩà¤ķर
    0.07
    ÙĦÙĬÙħ
    0.07
    à¹ĭ
    0.07
    èªĩ
    0.07
    дÑĢе
    0.07
    ungan
    0.07
    Activations Density 0.007%

    No Known Activations