© 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. 45148
    Prev
    Next
    INDEX
    Explanations

    extra numbers

    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
    uzzi
    -0.09
    åįĥçĻ¾
    -0.08
    edy
    -0.08
    æľĢ大åĬŁçİĩ
    -0.08
    hofer
    -0.08
    _series
    -0.08
    oja
    -0.08
    isoft
    -0.08
    ymp
    -0.08
    èµ°é«ĺ
    -0.07
    POSITIVE LOGITS
     extra
    0.08
     Extra
    0.07
    åĴĮä¸Ģ个
    0.07
    extra
    0.07
    -sided
    0.07
    (extra
    0.07
     extras
    0.07
    é¢Ŀå¤ĸçļĦ
    0.06
    alus
    0.06
     EXTRA
    0.06
    Activations Density 0.033%

    No Known Activations