© 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. 21507
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
    ä¸ºçĽ®çļĦ
    -0.08
    vä
    -0.07
    EEE
    -0.07
    äºīä¼ĺ
    -0.07
    ä¸Ń游
    -0.07
    /]
    -0.07
    icka
    -0.07
    icker
    -0.07
    )$/
    -0.07
    ick
    -0.07
    POSITIVE LOGITS
    ilding
    0.08
    reti
    0.08
    _typeof
    0.07
    éŀ
    0.07
    rog
    0.07
    subpackage
    0.07
    åĿIJ
    0.06
    æİ¥
    0.06
    áģĭ
    0.06
    tida
    0.06
    Activations Density 0.025%

    No Known Activations