© 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. 47883
    Prev
    Next
    INDEX
    Explanations

    elements consisting of

    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
    rag
    -0.07
    éĢłåĮĸ
    -0.07
    ä¸Ĭ好
    -0.07
    综åIJĪèĢĥèĻij
    -0.06
    ä¹Ŀ天
    -0.06
    _DRIVER
    -0.06
    ance
    -0.06
    责任åįķä½į
    -0.06
    _CONNECT
    -0.06
    haj
    -0.06
    POSITIVE LOGITS
    士
    0.09
    oggles
    0.08
    _toggle
    0.07
    æ²¼
    0.07
    ==$
    0.07
    Vect
    0.07
    Toggle
    0.07
    ownt
    0.07
     Bij
    0.07
    ä¸ĵèģĮ
    0.07
    Activations Density 0.010%

    No Known Activations