© 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. 50495
    Prev
    Next
    INDEX
    Explanations

    Committee Form

    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
    leyen
    -0.07
    æĢ»ä¸įèĥ½
    -0.07
    ä¹ĭäºİ
    -0.07
    illo
    -0.06
    iw
    -0.06
    ler
    -0.06
    æľºæ¢°
    -0.06
    ILD
    -0.06
    زÛĮ
    -0.06
    è¡£
    -0.06
    POSITIVE LOGITS
    é«ĺå¯Ĩ
    0.07
    碧çİī
    0.07
    æĻļæľŁ
    0.07
    amana
    0.07
    æģº
    0.07
    Äģja
    0.07
    èIJĬ
    0.07
    èݱ
    0.07
    çļĪ
    0.07
    交æĺĵä¼ļ
    0.07
    Activations Density 0.001%

    No Known Activations