© 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. 47701
    Prev
    Next
    INDEX
    Explanations

    the [adjective]

    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
    ï¸ı
    -0.07
    /vendors
    -0.07
    udu
    -0.07
    à¹Ģหล
    -0.07
     ساخ
    -0.07
    Ả
    -0.07
    çļĦçľ¼
    -0.07
    ÙĪÙĬا
    -0.07
    ãģ³
    -0.07
    uters
    -0.07
    POSITIVE LOGITS
    âĺħâĺĨ
    0.07
     *.
    0.06
    夯å®ŀ
    0.06
    éļĶ
    0.06
    裸
    0.06
    èĢģå¦Ī
    0.06
    éĤ£æŶ
    0.06
    æĪijäºĨ
    0.06
    ä»Ļåı°
    0.06
    ETS
    0.06
    Activations Density 1.083%

    No Known Activations