© 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. 23249
    Prev
    Next
    INDEX
    Explanations

    finger following words

    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
    ULER
    -0.10
    ê¹IJ
    -0.10
    quist
    -0.09
    sstr
    -0.09
    ìŀİ
    -0.09
    çĸ¸
    -0.08
    contre
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
    kül
    -0.08
    ×ŀ×ķ×ĵ
    -0.08
    POSITIVE LOGITS
    çļĦå°±æĺ¯
    0.14
    çļĦéĥ½æĺ¯
    0.10
    ings
    0.10
    çļĦä¸įæĺ¯
    0.08
    ä»Ģä¹Īåij¢
    0.08
    çļĦå°±
    0.08
    :
    0.07
    nt
    0.07
     облаÑģÑĤи
    0.07
    人æĪĸ
    0.07
    Activations Density 0.006%

    No Known Activations