© 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. 23112
    Prev
    Next
    INDEX
    Explanations

    sayexactlymost

    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
    åı¯æģ¶
    -0.08
     seolah
    -0.07
    å¡ĺéķĩ
    -0.07
    ä»¿ä½Ľæĺ¯
    -0.07
    borough
    -0.07
    好似
    -0.07
    æĪijä¸Ģå®ļè¦ģ
    -0.07
    iets
    -0.07
    çļĦä¸ĢåĪĩ
    -0.07
    å½±åŁİ
    -0.07
    POSITIVE LOGITS
    ä¸į太好
    0.08
     неплоÑħо
    0.07
    åĬĿ
    0.07
    รม
    0.07
     indeed
    0.07
    å°±åĪ«
    0.06
    úr
    0.06
     eher
    0.06
    ÑĤÑĸм
    0.06
    Indeed
    0.06
    Activations Density 0.969%

    No Known Activations