© 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. 11567
    Prev
    Next
    INDEX
    Explanations

    cron job, config, domains, job, tools

    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
    ä¿¡å¿ĥåĴĮ
    -0.07
    ules
    -0.07
    çļĦä¿¡å¿ĥ
    -0.07
    γκα
    -0.07
    -bre
    -0.07
    ×ijר×Ķ
    -0.07
     dec
    -0.06
    缸ç»ĵåIJĪçļĦæĸ¹å¼ı
    -0.06
     l
    -0.06
    croft
    -0.06
    POSITIVE LOGITS
    æĢĿæºIJ
    0.07
    麹
    0.07
    bian
    0.07
     Zem
    0.07
    çĪ±ä¸ĬäºĨ
    0.07
    çĮ¬
    0.07
    ç¼ĵ
    0.07
    aise
    0.07
    য়à§ĩ
    0.07
    tó
    0.06
    Activations Density 1.020%

    No Known Activations