© 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. 41733
    Prev
    Next
    INDEX
    Explanations

    adrenaline and catecholamines

    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
    çĤ¬
    -0.09
     mosaic
    -0.08
    çł¥
    -0.07
    miet
    -0.07
    mos
    -0.07
    žd
    -0.07
    ÚĨار
    -0.07
    çĴ¨
    -0.07
    åı£æ°´
    -0.07
    é©¬èµĽ
    -0.07
    POSITIVE LOGITS
    èĤ¾ä¸Ĭèħº
    0.10
     adrenaline
    0.09
    åĴĸåķ¡åĽł
    0.09
     caffe
    0.08
     caffeine
    0.08
    uille
    0.08
    æĮ¯å¥ĭ
    0.08
    udos
    0.08
    åħ´å¥ĭ
    0.08
    icot
    0.08
    Activations Density 0.116%

    No Known Activations