© 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. 50729
    Prev
    Next
    INDEX
    Explanations

    all possible combinations or values

    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
    æĬŀ
    -0.07
    éĺħ读éĩı
    -0.06
    Inputs
    -0.06
    ede
    -0.06
    enhagen
    -0.06
    åķ¼
    -0.06
    çļĦæ°´åĪĨ
    -0.06
    åĩłä¸ĭ
    -0.06
    oha
    -0.06
    chein
    -0.06
    POSITIVE LOGITS
    _sorted
    0.10
    符åIJĪæĿ¡ä»¶çļĦ
    0.10
     sorted
    0.10
    ToList
    0.09
    Sorted
    0.09
    åīĶ
    0.09
    .filtered
    0.09
    ä¹Łä¸įå¤ļ
    0.09
    滤
    0.09
    æīĢæľīçļĦ
    0.08
    Activations Density 0.056%

    No Known Activations