© 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. 19988
    Prev
    Next
    INDEX
    Explanations

    DA receptors

    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
    dux
    -0.08
    ordi
    -0.08
    à¹ģละà¸Ħวาม
    -0.08
    à¹ģละà¹Ģà¸Ľà¹ĩà¸Ļ
    -0.08
    åĴĮ对
    -0.08
    ìĿ´ìŀIJ
    -0.07
    íĻĶìĻĢ
    -0.07
    她åĴĮ
    -0.07
    MESS
    -0.07
    çĸ«æĥħéĺ²æݧåĴĮ
    -0.07
    POSITIVE LOGITS
     alike
    0.15
    两èĢħ
    0.13
    åIJĦèĩª
    0.12
    äºĮèĢħ
    0.12
    åīįèĢħ
    0.11
    缺ä¸Ģä¸įåı¯
    0.11
    两èĢħçļĦ
    0.11
    åIJİèĢħ
    0.11
    åħ±åIJĮ
    0.11
     respectively
    0.11
    Activations Density 0.147%

    No Known Activations