© 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. 32772
    Prev
    Next
    INDEX
    Explanations

    combination or coupling

    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
    å¿
    -0.08
    arken
    -0.07
    纵
    -0.07
    åIJIJ
    -0.07
     nữa
    -0.07
    ä½ĨåıĪ
    -0.06
    åIJĥåIJĥ
    -0.06
    )((((
    -0.06
    çį
    -0.06
    orso
    -0.06
    POSITIVE LOGITS
    /or
    0.09
    /OR
    0.09
    ãģ®ãģĶ
    0.08
    ché
    0.08
    æŀĦæĪIJçļĦ
    0.08
    /of
    0.08
    hing
    0.07
    éħįç½®æĸ¹éĿ¢
    0.07
    amp
    0.07
    ânt
    0.07
    Activations Density 0.274%

    No Known Activations