© 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. 55822
    Prev
    Next
    INDEX
    Explanations

    smell and related scents

    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
    appable
    -0.08
    éĿ¢åĢĴ
    -0.08
    ìĭ¬ìľ¼ë¡ľ
    -0.08
    žd
    -0.08
    zeg
    -0.07
    orsch
    -0.07
    éĽ¹
    -0.07
    åĮķ
    -0.07
     smoothly
    -0.07
    utton
    -0.07
    POSITIVE LOGITS
    æīijé¼»
    0.15
     запаÑħ
    0.12
     odor
    0.12
    éĹ»åĪ°
    0.12
     smell
    0.12
     scent
    0.12
     smells
    0.12
    æ°Ķåij³
    0.12
     aroma
    0.11
     smelling
    0.11
    Activations Density 0.071%

    No Known Activations