© 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. 63231
    Prev
    Next
    INDEX
    Explanations

    IBAction sender clicked

    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
    Ĩµ
    -0.07
     Pue
    -0.07
    è¿Ķ
    -0.06
    azzi
    -0.06
    P
    -0.06
    å¿ħä¸įåı¯
    -0.06
    Put
    -0.06
     P
    -0.06
    ç§Ģ丽
    -0.06
    uru
    -0.06
    POSITIVE LOGITS
     clicked
    0.09
    Clicked
    0.09
    触åıij
    0.09
     trigger
    0.09
    è¡ĮåĬ¨ä¸Ń
    0.08
     action
    0.08
    äºĭ件ä¸Ń
    0.08
    _click
    0.08
     клик
    0.08
    trigger
    0.08
    Activations Density 0.282%

    No Known Activations