© 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. 21683
    Prev
    Next
    INDEX
    Explanations

    physical measurements

    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
    trys
    -0.08
    lander
    -0.07
     “
    -0.06
     Tat
    -0.06
     ke
    -0.06
     Gem
    -0.06
    çİĦå¾·
    -0.06
    è±ļ
    -0.06
    æŀ¶ä¸Ĭ
    -0.06
    篷
    -0.06
    POSITIVE LOGITS
     Ratio
    0.09
    è¿Ľè¡Įæ¯Ķè¾ĥ
    0.09
    æ¯Ķäºļ
    0.09
     ratio
    0.08
    走好
    0.08
    ingular
    0.08
    æ¯Ķçİĩ
    0.08
    ratio
    0.08
    Ratio
    0.08
    esten
    0.08
    Activations Density 0.215%

    No Known Activations