© 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. 21334
    Prev
    Next
    INDEX
    Explanations

    NMDA receptor glutamate neurotransmission

    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
    éĿĴåŁİ
    -0.08
    éĢłçº¸
    -0.08
     Massa
    -0.07
    ogui
    -0.07
    imity
    -0.07
    åĸľæĢĴ
    -0.07
    åĸľä¹IJ
    -0.07
    çļĦè°ĥæķ´
    -0.07
    è°ĥæķ´åIJİ
    -0.07
    irr
    -0.07
    POSITIVE LOGITS
     synaptic
    0.08
    åIJĪéĩij
    0.07
    meth
    0.07
    ocere
    0.07
     transient
    0.07
    ัà¸Ī
    0.07
    odne
    0.07
     trance
    0.07
    Transient
    0.07
    ä½
    0.07
    Activations Density 0.064%

    No Known Activations