© 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. 10523
    Prev
    Next
    INDEX
    Explanations

    words ending in ization followed by of or and

    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
    ä»»ä½ķä¸ľè¥¿
    -0.08
    szy
    -0.08
    ÙģÙĪر
    -0.08
    yron
    -0.08
    -divider
    -0.07
    обе
    -0.07
    agnol
    -0.07
    ublik
    -0.07
    à¸ģีà¹Ī
    -0.07
    steller
    -0.07
    POSITIVE LOGITS
    ä¸İåºĶçĶ¨
    0.08
    åıĬåºĶçĶ¨
    0.07
    åĴĮå®ĮåĸĦ
    0.07
    åĴĮä¼ĺåĮĸ
    0.07
    åĴĮæĶ¹è¿Ľ
    0.07
    åĴĮæıIJé«ĺ
    0.07
    åĴĮåºĶçĶ¨
    0.06
    åĴĮè¦ģæ±Ĥ
    0.06
    zó
    0.06
     of
    0.06
    Activations Density 0.700%

    No Known Activations