© 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. 32705
    Prev
    Next
    INDEX
    Explanations

    organic functional groups and compounds

    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
    æĹ
    -0.07
    ä½łæĺ¯æĪijçļĦ
    -0.07
    âĢij
    -0.07
    大åħ¸
    -0.07
    <&
    -0.07
    uvi
    -0.07
    åİĤéķ¿
    -0.07
    fffffff
    -0.07
     rach
    -0.06
    çľĭ书
    -0.06
    POSITIVE LOGITS
    è¿ŀ
    0.08
     Postar
    0.08
    ÑĢÑıдо
    0.07
    universal
    0.07
    ystal
    0.07
    iente
    0.07
     universal
    0.07
    éĢ£
    0.07
     ÏĥÏĦι
    0.07
    “-
    0.07
    Activations Density 0.282%

    No Known Activations