© 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. 56373
    Prev
    Next
    INDEX
    Explanations

    industry

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    ony
    -0.07
    æĹ¥ä»¥æĿ¥
    -0.07
    antal
    -0.06
     ens
    -0.06
    ä¸ŃçļĦä»»æĦı
    -0.06
    çĶ¸
    -0.06
    ÑĨиона
    -0.06
    èĻij
    -0.06
    atively
    -0.06
    POSITIVE LOGITS
    å°Ķå¤ļ
    0.08
     often
    0.08
    è¿ĻæŶçļĦ
    0.08
     spesso
    0.07
    ureau
    0.07
    orse
    0.07
     costum
    0.07
    åĬ¨ä¸įåĬ¨
    0.07
    ä¹Łæĺ¯å¦ĤæѤ
    0.07
    zer
    0.07
    Activations Density 0.015%

    No Known Activations