© 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. 57458
    Prev
    Next
    INDEX
    Explanations

    kinase and enzyme inhibitors

    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
    çĦī
    -0.07
     attrib
    -0.07
    ITU
    -0.07
    èij©
    -0.06
    çĢ
    -0.06
     Roos
    -0.06
    STER
    -0.06
     disconnected
    -0.06
    æľīä¸ĢèĤ¡
    -0.06
    éħ¸çĶľ
    -0.06
    POSITIVE LOGITS
     targets
    0.10
    -target
    0.10
     inhibitor
    0.10
    éĿ¶
    0.10
     inhibition
    0.09
    adaran
    0.09
     inhibitors
    0.09
    æĬijåĪ¶åīĤ
    0.09
     target
    0.08
     sasaran
    0.08
    Activations Density 0.370%

    No Known Activations