© 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. 29476
    Prev
    Next
    INDEX
    Explanations

    base implementation class extension

    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
    иви
    -0.08
    æĪIJ为ä¸Ģç§į
    -0.07
    åŀ£
    -0.07
    çļĦéĤ£ç§į
    -0.07
    obody
    -0.07
    çļĦéĤ£ä¸ª
    -0.07
    æĸ°çļĦæĮijæĪĺ
    -0.07
    vania
    -0.07
    alaman
    -0.07
    å®ĥ们æĺ¯
    -0.07
    POSITIVE LOGITS
    çĶ¨äºİ
    0.06
    icka
    0.06
     zur
    0.06
    \\.
    0.06
    iced
    0.06
    缮çļĦåľ¨äºİ
    0.06
    æĹ¨åľ¨
    0.06
    azin
    0.06
    umm
    0.06
    patrick
    0.06
    Activations Density 0.094%

    No Known Activations