© 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. 33616
    Prev
    Next
    INDEX
    Explanations

    True, False, Yes, No

    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
    ev
    -0.07
    鼷æĸ¯
    -0.07
    ilh
    -0.06
    çļĦä¸įèī¯
    -0.06
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    -0.06
    года
    -0.06
     Blair
    -0.06
    rane
    -0.06
    ilat
    -0.06
    оÑĤоÑĢ
    -0.06
    POSITIVE LOGITS
    对éĶĻ
    0.09
    ìĭľìĺ¤
    0.09
    viet
    0.08
    踵
    0.08
    æĪĸæĺ¯
    0.08
    astes
    0.08
    館
    0.08
    æĬijæĪĸ
    0.08
    arness
    0.07
    ¿IJ
    0.07
    Activations Density 0.006%

    No Known Activations