© 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. 9341
    Prev
    Next
    INDEX
    Explanations

    event handlers like onclick

    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
    aner
    -0.07
     Acu
    -0.07
    çĽ¸æľĽ
    -0.07
    é£ĺèį¡
    -0.07
    iterated
    -0.07
    èĽ¹
    -0.07
     Mate
    -0.07
    ALLOC
    -0.07
    使çĶ¨åīį
    -0.07
    aksa
    -0.07
    POSITIVE LOGITS
    ç«ĭåĪ»
    0.08
    .toggle
    0.08
     trigger
    0.08
     triggered
    0.08
    _triggered
    0.08
    触åıij
    0.08
    äºĭ件ä¸Ń
    0.07
     instantly
    0.07
    æ·¡
    0.07
     action
    0.07
    Activations Density 0.291%

    No Known Activations