© 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. 25419
    Prev
    Next
    INDEX
    Explanations

    statistical terms

    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
    à¦
    -0.08
    ilter
    -0.08
    åѦä¼ļ
    -0.07
    arness
    -0.07
    cci
    -0.07
    å°Ħç²¾
    -0.07
    য়à§ĩর
    -0.07
    azionale
    -0.07
    Leaks
    -0.07
    ä¸įåĸĦ
    -0.07
    POSITIVE LOGITS
     berupa
    0.08
    ces
    0.07
    é£İåĴĮ
    0.07
    ryo
    0.07
    åıĬåħ¶
    0.07
    æ³ķ
    0.07
    à¸ģà¸²à¸£à¸Ľà¸£à¸°à¸Ĭุม
    0.07
    åĴĮæĸ¹æ³ķ
    0.07
    (s
    0.07
    å¾Ģ
    0.06
    Activations Density 0.001%

    No Known Activations