© 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. 39941
    Prev
    Next
    INDEX
    Explanations

    have followed by verb or noun phrase

    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
    ä½łæķ¢
    -0.07
     Ñħода
    -0.06
    æīĢ欲
    -0.06
    rovers
    -0.06
     Nights
    -0.06
     disp
    -0.06
    Ñijн
    -0.06
    ettare
    -0.06
     whence
    -0.06
     fil
    -0.06
    POSITIVE LOGITS
    ercul
    0.07
     súper
    0.07
    ürn
    0.07
    >>)
    0.07
    hun
    0.07
    èIJĮèIJĮ
    0.07
     пÑĢиÑĩ
    0.07
    åĴĮ大家åĪĨ享
    0.07
    äºijé£ŀ
    0.07
    é£ŀæĿ¥
    0.07
    Activations Density 0.001%

    No Known Activations