© 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. 57682
    Prev
    Next
    INDEX
    Explanations

    accessibility, screen reader, focus, tab

    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
    æķĪæŀľåĽ¾
    -0.08
    Õ®
    -0.07
    _DROP
    -0.06
    御
    -0.06
    ä¸ĭ载次æķ°
    -0.06
    mill
    -0.06
    ÐIJнд
    -0.06
    è¬Ŀ
    -0.06
    PHY
    -0.06
    tsy
    -0.06
    POSITIVE LOGITS
     accessibility
    0.11
     Accessibility
    0.10
    æĹłéļľç¢į
    0.10
    çĽ²äºº
    0.10
    Accessibility
    0.09
     semantic
    0.09
    çĽ²
    0.09
    æ®ĭçĸ¾äºº
    0.09
     blindness
    0.09
    ixel
    0.08
    Activations Density 0.053%

    No Known Activations