© 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. 26887
    Prev
    Next
    INDEX
    Explanations

    programming keywords and modules

    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
    umont
    -0.08
    秣èµģä½ıæĪ¿
    -0.08
    lipp
    -0.08
    æŶèĩ³ä»Ĭ
    -0.08
    å°½æľī
    -0.08
    jen
    -0.07
    çļĦæŶåĢĻäºĨ
    -0.07
    ä¹ĺçĶ¨è½¦
    -0.07
    丽åįİ
    -0.07
    mund
    -0.07
    POSITIVE LOGITS
    alto
    0.07
     closely
    0.06
    ï¼Į
    0.06
    åħĪ
    0.06
     disclosed
    0.06
    ä¸įå®ī
    0.06
    被
    0.06
     six
    0.06
    A
    0.06
    itations
    0.06
    Activations Density 0.662%

    No Known Activations