© 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. 13239
    Prev
    Next
    INDEX
    Explanations

    strict mode code

    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
    hood
    -0.08
    ãĥªãĥĥãĤ¯
    -0.08
    itive
    -0.08
    ä½łè¯´çļĦ
    -0.08
    aire
    -0.08
    oret
    -0.08
    zug
    -0.08
    ary
    -0.07
    hejiang
    -0.07
    æł·çļĦ
    -0.07
    POSITIVE LOGITS
     chẽ
    0.12
    ä¸į严
    0.08
    ç¨ĭ度
    0.08
    ests
    0.08
    issimi
    0.08
    ç»Ĩèĩ´
    0.08
    ç»Ĩèĩ´çļĦ
    0.08
    ä¸įä½ı
    0.08
    ented
    0.07
     ngặt
    0.07
    Activations Density 0.037%

    No Known Activations