© 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. 39822
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or separators

    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
    æĺ¥ç¬ĭ
    -0.07
    ini
    -0.07
    inius
    -0.06
     interv
    -0.06
    Refs
    -0.06
    åĪ¶
    -0.06
     abbr
    -0.06
    iniz
    -0.06
    achel
    -0.06
     خاÙħ
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.10
    again
    0.09
    ollo
    0.09
    类似çļĦ
    0.09
    åIJĮæł·çļĦ
    0.08
    åIJĮæł·æĺ¯
    0.08
     Buckley
    0.08
     again
    0.08
    è°ģçŁ¥
    0.08
    yo
    0.08
    Activations Density 0.337%

    No Known Activations