© 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. 47502
    Prev
    Next
    INDEX
    Explanations

    mathematical functions exp and ln

    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
    以ä¸ĭåĨħ容
    -0.07
    PM
    -0.07
    رة
    -0.07
    åĿļå®ļçIJĨæĥ³ä¿¡å¿µ
    -0.07
    عداد
    -0.07
    æĢ»æĶ¯
    -0.06
    ĥ
    -0.06
    ML
    -0.06
    esis
    -0.06
    æĽ´å¤§çļĦè´¡çĮ®
    -0.06
    POSITIVE LOGITS
    /tutorial
    0.07
     discharge
    0.07
    ioni
    0.06
    èķ
    0.06
    èĭ
    0.06
    æĶ¾çĶµ
    0.06
    çŁ¥
    0.06
    untime
    0.06
     bel
    0.06
    交货
    0.06
    Activations Density 0.003%

    No Known Activations