© 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. 64973
    Prev
    Next
    INDEX
    Explanations

    enzymes oxidation maillard protein

    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
    èļĬåŃIJ
    -0.08
    ä¸įéĻIJ
    -0.08
     magari
    -0.07
     landsc
    -0.07
     Beno
    -0.07
     padded
    -0.07
    ç¯ĨåĪ»
    -0.07
    çĹŀ
    -0.07
    Slinky
    -0.07
    çĩĥ
    -0.07
    POSITIVE LOGITS
     proteins
    0.10
    èĽĭçĻ½è´¨
    0.09
    天éŨ
    0.08
     USDA
    0.08
     protein
    0.08
    èĽĭçĻ½
    0.07
     preco
    0.07
    表å±Ĥ
    0.07
    åĨľä¸ļ大åѦ
    0.07
     Instant
    0.07
    Activations Density 0.188%

    No Known Activations