© 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. 8775
    Prev
    Next
    INDEX
    Explanations

    do you/I/your/is your/are you/are your questions

    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
    ery
    -0.07
    ider
    -0.07
    zel
    -0.07
    ing
    -0.06
    ick
    -0.06
    ikus
    -0.06
    æĭħ
    -0.06
    áĢĦáĢ¹áĢ¸
    -0.06
    èģĶåIJĪä¼ļ
    -0.06
    æİĪ
    -0.06
    POSITIVE LOGITS
    å¯Ħ
    0.08
    acqu
    0.08
    zza
    0.07
    ytte
    0.07
    हार
    0.07
    ä¸įä¸Ģ
    0.07
    nose
    0.07
    astreet
    0.07
    ä½¼
    0.07
    anaman
    0.07
    Activations Density 0.001%

    No Known Activations