© 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. 57771
    Prev
    Next
    INDEX
    Explanations

    Mek/å¯Ĵ/ä¸ĢåĪĩçļĦ/ople/BuilderFactory

    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
    rade
    -0.08
    sd
    -0.07
    èĮ¬
    -0.07
    heds
    -0.07
    Äĥmânt
    -0.07
    ä¸įèIJ½
    -0.07
    ä¸įèĩª
    -0.07
    urn
    -0.06
    andar
    -0.06
    adan
    -0.06
    POSITIVE LOGITS
     Mek
    0.07
    å¯Ĵ
    0.06
    ä¸ĢåĪĩçļĦ
    0.06
    ople
    0.06
    BuilderFactory
    0.06
    /Delete
    0.06
    à¹Īà¸Ńà¸Ļ
    0.06
     hypo
    0.06
    rier
    0.06
    ä¸Ńå¿ĥçŃī
    0.06
    Activations Density 0.001%

    No Known Activations