© 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. 22816
    Prev
    Next
    INDEX
    Explanations

    database indexing and models

    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
    çĦ¶æĺ¯
    -0.08
    æĺ¯ä¸Ģå¼ł
    -0.07
    åı¯ä»¥éĻįä½İ
    -0.07
    åı¯éĻįä½İ
    -0.07
    daq
    -0.07
    åľ¨åĵªéĩĮ
    -0.06
    åĸľéĹ»
    -0.06
    åĪ°åĵª
    -0.06
    çĸ±
    -0.06
    ifty
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥĦ
    0.07
    egos
    0.07
    даÑĤ
    0.07
    俱ä¹IJéĥ¨
    0.07
    вед
    0.07
     Wach
    0.07
    oges
    0.07
    -ext
    0.07
    their
    0.07
    dry
    0.06
    Activations Density 0.051%

    No Known Activations