© 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. 8214
    Prev
    Next
    INDEX
    Explanations

    dates and months

    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
    icali
    -0.07
    翼翼
    -0.07
    ä¸´æ±Ł
    -0.07
    eda
    -0.06
    å»·
    -0.06
    Matchers
    -0.06
    oler
    -0.06
    éĸij
    -0.06
    æĢ§çļ®èĤ¤çĹħ
    -0.06
     Hr
    -0.06
    POSITIVE LOGITS
    Äħż
    0.07
    ebbe
    0.07
    à¹īวà¸Ļ
    0.07
    å°ıæīĭ
    0.07
    bola
    0.07
    mit
    0.06
    çľ¼éĩĮ
    0.06
    upe
    0.06
    inde
    0.06
    æĹ©æĻļ
    0.06
    Activations Density 0.057%

    No Known Activations