© 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. 49937
    Prev
    Next
    INDEX
    Explanations

    PDT, BST, Indochina

    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
    æ¦ľ
    -0.08
    ioni
    -0.08
    èļ¤
    -0.07
    alum
    -0.07
    _COMPONENT
    -0.07
    ghi
    -0.07
    è¾Ī
    -0.07
    ä½łæĺ¯ä¸ª
    -0.07
    å°¼å°Ķ
    -0.07
    çķª
    -0.07
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯
    0.09
    æľ¨çĵľ
    0.08
    /UI
    0.07
    åį³
    0.07
    åį³åľ¨
    0.07
    åı¯å¢ŀåĬł
    0.07
    enso
    0.07
    /W
    0.07
    rlen
    0.07
    稻èįī
    0.07
    Activations Density 0.042%

    No Known Activations