© 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. 50234
    Prev
    Next
    INDEX
    Explanations

    universe, vastness, cosmos

    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
    åľ¨çİ°åľº
    -0.08
     Swagger
    -0.07
    æĬĬéĴ±
    -0.07
     immobil
    -0.07
    åľ¨ç¤¾åĮº
    -0.07
     injury
    -0.07
    å°ıæīĭ
    -0.07
     Injury
    -0.07
    Locker
    -0.07
    éĿłåľ¨
    -0.07
    POSITIVE LOGITS
    å®ĩå®ĻçļĦ
    0.10
    /world
    0.10
     billions
    0.10
     universe
    0.09
    å®ĩå®Ļ
    0.09
     infinite
    0.09
    ä¸ĸçķĮçļĦ
    0.09
     vast
    0.08
     cosmic
    0.08
     cosm
    0.08
    Activations Density 0.012%

    No Known Activations