© 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. 58501
    Prev
    Next
    INDEX
    Explanations

    chemical structure-activity relationship

    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
     fid
    -0.08
     Fid
    -0.07
    iak
    -0.07
    ID
    -0.07
    OrNil
    -0.07
    orr
    -0.07
     undefined
    -0.06
     vox
    -0.06
    ä¸īéĿ¢
    -0.06
    صاب
    -0.06
    POSITIVE LOGITS
     comparative
    0.11
     comparisons
    0.11
    Compar
    0.11
     Compar
    0.10
     comparing
    0.10
     ÑģÑĢавни
    0.10
     compareTo
    0.10
    åIJĮ为
    0.10
     comparison
    0.10
    Compare
    0.10
    Activations Density 0.042%

    No Known Activations