© 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. 9392
    Prev
    Next
    INDEX
    Explanations

    steroids or inhibitors

    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
    æľ
    -0.07
    åĴĮæݧåĪ¶
    -0.07
     populated
    -0.07
    èĶĹ
    -0.06
    ä¸Ģ个个
    -0.06
    大好
    -0.06
    çijľ
    -0.06
     пÑĢибоÑĢ
    -0.06
    éĢļè¿ĩåĪĨæŀIJ
    -0.06
    [][]
    -0.06
    POSITIVE LOGITS
     either
    0.09
    either
    0.09
     либо
    0.09
     combination
    0.08
     âī¥
    0.08
     regimen
    0.08
     seul
    0.08
    Either
    0.08
    çļĦç»ĦåIJĪ
    0.08
    æĸ¹æ¡Ī
    0.08
    Activations Density 0.319%

    No Known Activations