© 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. 18596
    Prev
    Next
    INDEX
    Explanations

    command types

    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
    åŃ£åIJİ
    -0.07
    ÄĻt
    -0.06
    æĸĩç«łæłĩçŃ¾
    -0.06
    utherland
    -0.06
     consc
    -0.06
    çĭ¡
    -0.06
    weeney
    -0.06
     /></
    -0.06
    ä¸Ģ大æī¹
    -0.06
    èĻ«èįī
    -0.06
    POSITIVE LOGITS
    commands
    0.08
    åĨĴ
    0.07
    åij½ä»¤
    0.07
     EventType
    0.07
    æĮĩ令
    0.07
    幡
    0.07
    åĬŁèĥ½æĺ¯
    0.07
    _EMIT
    0.07
    æŶéļĶ
    0.07
    ç±»åŀĭçļĦ
    0.07
    Activations Density 0.018%

    No Known Activations