© 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. 51745
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

    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
    avu
    -0.07
    ä¸ĬåĽ¾
    -0.06
    ä¸Ģ举
    -0.06
     infatti
    -0.06
    _*
    -0.06
    aska
    -0.06
     Johnston
    -0.06
    ↵
    -0.06
    çļĦå·¥ä½ľæĢģ度
    -0.06
    UCH
    -0.05
    POSITIVE LOGITS
    izr
    0.09
    öö
    0.08
     drauf
    0.08
    _esc
    0.08
    ever
    0.07
    æŁIJä¸Ģ天
    0.07
    à¤ĸा
    0.07
    HCM
    0.07
    é½
    0.07
    TX
    0.07
    Activations Density 0.008%

    No Known Activations