© 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. 9423
    Prev
    Next
    INDEX
    Explanations

    number and volume prefixes

    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
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    (
    -0.06
     Romana
    -0.06
     procedure
    -0.06
    Lik
    -0.06
    为åİŁæĸĻ
    -0.06
     Thrones
    -0.06
    VERIFY
    -0.06
    èĢĮæĺ¯è¦ģ
    -0.06
    å·¥èµĦçļĦ
    -0.06
    POSITIVE LOGITS
    Cover
    0.08
    eraus
    0.08
    åħ¨ç³»åĪĹ
    0.08
    ıra
    0.08
    åľ°åĿĢä½įäºİ
    0.08
    ļľ
    0.07
    ائÛĮ
    0.07
     proudly
    0.07
     hinein
    0.07
     Niest
    0.07
    Activations Density 0.448%

    No Known Activations