© 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. 9061
    Prev
    Next
    INDEX
    Explanations

    off / away / back / discharged / closed

    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
    ìĹ½
    -0.08
    coa
    -0.08
    enca
    -0.08
    entr
    -0.07
    åľ¨ä¼ļä¸Ĭ
    -0.07
    entra
    -0.07
    ÙĪسÛĮ
    -0.07
    åĪ°è¾¾äºĨ
    -0.07
    顺åĪ©çļĦ
    -0.07
    æīĢ欲è¨Ģ
    -0.07
    POSITIVE LOGITS
    ä¹ĭä½Ļ
    0.07
    pty
    0.06
    iad
    0.06
    毫
    0.06
    æĤ£
    0.06
    rott
    0.06
    èIJ½åľ¨
    0.06
     breve
    0.06
    客è§Ĥ
    0.06
    转èĢĮ
    0.06
    Activations Density 0.169%

    No Known Activations