© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61929
    Prev
    Next
    INDEX
    Explanations

    mathematical generator

    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
    åģļå¾Ĺ
    -0.07
     Jakob
    -0.06
    Âł
    -0.06
     شاÙħÙĦ
    -0.06
    seed
    -0.06
    attan
    -0.06
    çļĦ缮æłĩ
    -0.06
    ä¸įä¿Ĺ
    -0.06
    trimmed
    -0.06
    æݸ
    -0.06
    POSITIVE LOGITS
    å´ĩæĭľ
    0.08
    eph
    0.07
    epy
    0.07
    设置为
    0.07
    λÏī
    0.07
     Dix
    0.07
    gest
    0.07
    isks
    0.07
    ajar
    0.07
     powers
    0.07
    Activations Density 0.009%

    No Known Activations