© 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. 20063
    Prev
    Next
    INDEX
    Explanations

    essential oils and scent

    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
    ritch
    -0.07
    æ·Ģ
    -0.07
    okok
    -0.07
    éĵģçļĦ
    -0.07
    åIJĥ
    -0.07
    ç³ĸå°¿
    -0.07
     اÙĦÙħسÙĦ
    -0.07
     Constructors
    -0.07
    é«ĺå¯Ĩ
    -0.07
    ç³Ł
    -0.07
    POSITIVE LOGITS
    精油
    0.14
     fragrance
    0.10
     aroma
    0.09
    é¦Ļæ°Ľ
    0.09
     scent
    0.09
    é¦Ļæ°´
    0.09
     inhal
    0.09
     VOC
    0.09
    é¦Ļæ°Ķ
    0.09
    æ°Ľ
    0.09
    Activations Density 0.036%

    No Known Activations