© 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. 19873
    Prev
    Next
    INDEX
    Explanations

    quantifying states and measures

    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
    æłĢ
    -0.08
    æĹ¥åĪ¶
    -0.07
    彤
    -0.07
    鬣
    -0.06
    à¹Ģหà¸ĩ
    -0.06
    راد
    -0.06
    æŁĴ
    -0.06
    eking
    -0.06
     vital
    -0.06
    åľ©
    -0.06
    POSITIVE LOGITS
    aton
    0.08
    æľīæĽ´å¤ļçļĦ
    0.08
    izoph
    0.07
    UnderTest
    0.07
    ä¸ĬæĿ¥çľĭ
    0.07
    arz
    0.07
    endt
    0.07
    essim
    0.07
    uja
    0.07
    impa
    0.07
    Activations Density 0.026%

    No Known Activations