© 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. 65506
    Prev
    Next
    INDEX
    Explanations

    suffixation of words

    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
    å¡ļ
    -0.08
    á»Ĺ
    -0.08
    tij
    -0.08
    ìį¨
    -0.08
    ieden
    -0.08
    baugh
    -0.07
    åĢ¼åĴĮ
    -0.07
    å´İ
    -0.07
    æ¦ľ
    -0.07
    ä¸Ńä¹ĭ
    -0.07
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.10
    lest
    0.08
    ness
    0.07
    æĸ°åĬłåĿ¡
    0.07
    ìĿ´ìħĺ
    0.06
     بÙĪدÙĨ
    0.06
    credi
    0.06
    ãĢģ“
    0.06
     شدÙĨ
    0.06
    亦æĪĸæĺ¯
    0.06
    Activations Density 0.391%

    No Known Activations