© 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. 38847
    Prev
    Next
    INDEX
    Explanations

    review of motor

    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
    çĻ¾éĩĮ
    -0.07
    atos
    -0.07
     Mas
    -0.07
    å·´å·´
    -0.07
    è¿IJä¼ļ
    -0.07
    aderos
    -0.06
     баÑĢ
    -0.06
    èĩ´è¿ľ
    -0.06
    èħ»
    -0.06
    æľī害
    -0.06
    POSITIVE LOGITS
    éŀĺ
    0.08
    åĵĢ
    0.08
    رÙĬد
    0.07
    è¾Ļ
    0.07
    çļĦ绣ä¸Ģ
    0.07
    echa
    0.07
    Benchmark
    0.07
    ибо
    0.07
    åĸĿå®Į
    0.06
    bler
    0.06
    Activations Density 0.548%

    No Known Activations