© 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. 39194
    Prev
    Next
    INDEX
    Explanations

    linear, nuclear, photon, cis, Gregorian, grayscale, overt, eared

    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
    æĹ¢çĦ¶æĺ¯
    -0.08
    лоÑģÑĤи
    -0.08
    hani
    -0.08
    åŃ¦ä¹łåħ´è¶£
    -0.08
    phin
    -0.08
    éĵ¿
    -0.07
    æ¯ı个åѦçĶŁ
    -0.07
     uÄŁ
    -0.07
    vait
    -0.07
    å¢ŀæ·»
    -0.07
    POSITIVE LOGITS
    æŃ£å¸¸çļĦ
    0.09
    æŃ£å¸¸
    0.09
    对çħ§
    0.08
     counterparts
    0.08
    çļĦæŃ£å¸¸
    0.07
    çħ§å¸¸
    0.07
    xFFFFFF
    0.07
    eday
    0.07
    venz
    0.07
    常æĢģ
    0.07
    Activations Density 0.321%

    No Known Activations