© 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. 63350
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
    çļĦæĺ¯ä¸Ģ个
    -0.06
    łĢ
    -0.06
    仲
    -0.06
    åĪ¶æĪIJ
    -0.06
    ä¸įä¸Ĭ
    -0.06
    åĵĪåĵĪåĵĪ
    -0.06
    oon
    -0.06
    大éĻĨçļĦ
    -0.06
    æľĢä¼Łå¤§çļĦ
    -0.06
    Ùħاع
    -0.06
    POSITIVE LOGITS
    ÛĮدÙĩ
    0.08
    类似çļĦ
    0.07
    ofil
    0.07
    INC
    0.07
    adin
    0.07
    -Cal
    0.07
     similarly
    0.07
    类似
    0.07
    éĿ
    0.07
    åIJĮçIJĨ
    0.07
    Activations Density 0.038%

    No Known Activations