© 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. 31924
    Prev
    Next
    INDEX
    Explanations

    optical imaging and illumination

    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
     âm
    -0.06
    ä¿ĿæķĻ
    -0.06
     written
    -0.06
     temporary
    -0.06
     season
    -0.06
    è®°äºĭ
    -0.06
    umul
    -0.06
     Escrit
    -0.06
    è¿ŀè¿ŀ
    -0.06
    æķ°æį®åŃĺåĤ¨
    -0.06
    POSITIVE LOGITS
     optics
    0.11
    æķ´å½¢
    0.09
     aperture
    0.09
    尺寸
    0.08
    çĭ
    0.08
    panse
    0.08
    åĽŀç¨ĭ
    0.08
    ÑĢаÑĤно
    0.08
    igmatic
    0.08
    尺寸çļĦ
    0.08
    Activations Density 0.037%

    No Known Activations