© 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. 2342
    Prev
    Next
    INDEX
    Explanations

    numbers following punctuation

    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
    æĥ³ä¸įåĪ°
    -0.06
    åį°
    -0.06
    esseract
    -0.06
    æį¢åıĸ
    -0.06
    åĽ¾åĴĮ
    -0.06
    षà¥į
    -0.06
    ks
    -0.05
     ÙĦÙħØ´
    -0.05
     Barcel
    -0.05
    åIJĦç§įåİŁåĽł
    -0.05
    POSITIVE LOGITS
    éĵ¶å±±
    0.08
    0.08
    ths
    0.08
    vét
    0.08
    лÑıÑĢ
    0.08
    tib
    0.07
    ï¸ı
    0.07
    人æ°ijåħ±åĴĮåĽ½
    0.07
    è¹Ī
    0.07
    ulet
    0.07
    Activations Density 0.023%

    No Known Activations