© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30273
    Prev
    Next
    INDEX
    Explanations

    etymology 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
    vente
    -0.09
    åĴĮåħ¶ä»ĸ
    -0.08
    polis
    -0.08
    çIJĨäºĭéķ¿
    -0.08
    vei
    -0.08
    寡
    -0.08
    мили
    -0.07
    ród
    -0.07
    ä¹ĭæĢ¥
    -0.07
    wijk
    -0.07
    POSITIVE LOGITS
    çļĦæĦıæĢĿ
    0.08
    ä»Ģä¹Īä¸ľè¥¿
    0.08
    un
    0.08
    äºĭçī©
    0.07
    ä¹ĭæĦı
    0.07
    
    0.07
     اÙĦØ´ÙĬØ¡
    0.07
    å¼ķçĶ³
    0.07
     things
    0.07
    äºĭçī©çļĦ
    0.07
    Activations Density 0.022%

    No Known Activations