© 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. 18669
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
     Bons
    -0.07
    oros
    -0.07
    ette
    -0.07
    hie
    -0.06
    ete
    -0.06
    eden
    -0.06
    _Manager
    -0.06
    hm
    -0.06
    å½ĵåīįçļĦ
    -0.06
    å¸ĤåľºåĴĮ
    -0.06
    POSITIVE LOGITS
    ayout
    0.07
    åºĻä¼ļ
    0.07
    辨è¯Ĩ
    0.07
    ายà¸Ļ
    0.07
    ç²¾æīĵ
    0.07
    .mozilla
    0.07
    æĦŁåĬ¨
    0.07
     turista
    0.07
    اÙģع
    0.06
    éķ¿éķ¿
    0.06
    Activations Density 0.010%

    No Known Activations