© 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. 20392
    Prev
    Next
    INDEX
    Explanations

    therefore hence which

    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
    æĪijåij¢
    -0.07
    ammen
    -0.07
     '.',
    -0.07
    ÙĩاÛĮÛĮ
    -0.07
    çļĦè¿Ļ个
    -0.06
     thereof
    -0.06
    thus
    -0.06
     ÙĨظر
    -0.06
    åĽłä¸ºæľīäºĨ
    -0.06
     '
    -0.06
    POSITIVE LOGITS
    ioni
    0.08
     ÙĥØ«ÙĬراÙĭ
    0.07
    åıĸãĤĬ
    0.07
    nek
    0.07
    çĿ¬
    0.07
    orio
    0.07
    缸éĢ¢
    0.07
    å°½ãģı
    0.07
    só
    0.07
    ÙĥÙĪ
    0.06
    Activations Density 0.001%

    No Known Activations