© 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. 41665
    Prev
    Next
    INDEX
    Explanations

    without using or revealing

    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
    cern
    -0.07
    å¦Ļãģª
    -0.07
    è¾ķ
    -0.07
    æķĻåŃ¦æ°´å¹³
    -0.07
    лаÑĤ
    -0.06
    WithEmail
    -0.06
    被æĴŀ
    -0.06
    oppen
    -0.06
    ัà¸Ķ
    -0.06
     "&#
    -0.06
    POSITIVE LOGITS
    פת
    0.07
    lington
    0.07
    öger
    0.07
    VS
    0.07
     VS
    0.06
    形象çļĦ
    0.06
    cule
    0.06
    oo
    0.06
    缴æİ¥çļĦ
    0.06
    antz
    0.06
    Activations Density 0.002%

    No Known Activations