© 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. 27097
    Prev
    Next
    INDEX
    Explanations

    integral notation

    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
    è°ĥæŁ¥ç»ĵæŀľ
    -0.07
    acon
    -0.06
    ierzch
    -0.06
     Padr
    -0.06
     Déf
    -0.06
    é¾ĻéŨ
    -0.06
     lẫn
    -0.06
    ataloader
    -0.06
    æĬī
    -0.06
    éºŁ
    -0.06
    POSITIVE LOGITS
     Pais
    0.08
    èݱ德
    0.08
    涯
    0.08
     اÙĦÙĨز
    0.08
    egend
    0.08
    éļ¾æ±Ĥ
    0.07
     pais
    0.07
    ries
    0.07
    æĶ»åħĭ
    0.07
    ×ĵ×Ŀ
    0.07
    Activations Density 0.006%

    No Known Activations