© 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. 2604
    Prev
    Next
    INDEX
    Explanations

    same / shared / uniform

    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
    åľ¨å¹³æŶ
    -0.08
    باب
    -0.07
    лд
    -0.07
    icht
    -0.07
    个人æĪĸ
    -0.07
    åħ·ä½ĵè¦ģæ±Ĥ
    -0.07
    ichten
    -0.07
    ابÙĬ
    -0.07
    éļıçĿĢ社ä¼ļ
    -0.07
    人æĿ¥
    -0.07
    POSITIVE LOGITS
     shared
    0.12
    åħ±åIJĮçļĦ
    0.12
    åħ±äº«
    0.10
    shared
    0.09
     uniform
    0.09
    åħ±çĶ¨
    0.09
    Shared
    0.09
     gemeinsame
    0.08
     gemeinsamen
    0.08
    åIJĮæŃ¥
    0.08
    Activations Density 0.013%

    No Known Activations