© 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. 63930
    Prev
    Next
    INDEX
    Explanations

    Docker, Marsh, plans, rights

    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
    åı¯èĥ½ä¼ļ对
    -0.08
    ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.08
    emm
    -0.07
    ä¸Ģå®ļç¨ĭ度
    -0.07
    åı¯èĥ½å¯¹
    -0.07
    åı¯èĥ½éľĢè¦ģ
    -0.07
     magari
    -0.07
    çĸijä¼¼
    -0.06
    æľīä¸Ģå®ļçļĦ
    -0.06
    -0.06
    POSITIVE LOGITS
    ziaÅĤ
    0.08
     именно
    0.08
     Ñģаме
    0.08
    çļĦå°±æĺ¯
    0.08
    ä¹ŁæŃ£æĺ¯
    0.08
     eben
    0.07
    åľ¨åį³
    0.07
    ostÃŃ
    0.07
    족
    0.07
     runnable
    0.07
    Activations Density 0.013%

    No Known Activations