© 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. 9669
    Prev
    Next
    INDEX
    Explanations

    rapidity gap

    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
    èĢ
    -0.07
     Dix
    -0.07
    imson
    -0.07
     enc
    -0.06
     soit
    -0.06
    inian
    -0.06
     bran
    -0.06
    igel
    -0.06
    оÑĢе
    -0.06
    å¼ı
    -0.06
    POSITIVE LOGITS
    ibl
    0.10
    é¢Ĩ导åıĬ
    0.08
    ekl
    0.08
    .Filter
    0.08
    wise
    0.08
    eldo
    0.08
    æĹ¥æĻļ
    0.08
    adr
    0.07
    ä¸ĩä½Ļåħĥ
    0.07
     wyr
    0.07
    Activations Density 0.005%

    No Known Activations