© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1372
    Prev
    Next
    INDEX
    Explanations

    scent and smell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittal
    -0.10
    ç«Ļç«ĭ
    -0.09
     japanese
    -0.09
    å±ŀå®ŀ
    -0.09
    çļĦ姿æĢģ
    -0.09
    ycz
    -0.09
    æĨĭ
    -0.09
    ocking
    -0.09
    ukkan
    -0.09
    ç½¢
    -0.09
    POSITIVE LOGITS
     smell
    0.13
     smells
    0.12
    æ°Ķåij³
    0.12
    弥漫
    0.12
     aroma
    0.11
     mùi
    0.11
    é¦Ļæ°Ķ
    0.11
    é¦Ļåij³
    0.11
    èģŀ
    0.11
    éĹ»
    0.10
    Activations Density 0.032%

    No Known Activations