© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 50331
    Prev
    Next
    INDEX
    Explanations

    fragrance, scent, perfume, 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
    å·´å·´
    -0.10
    åĸĤ
    -0.09
    mong
    -0.09
    ippy
    -0.09
    ç³į
    -0.09
    é£Ł
    -0.09
    é¥Ń
    -0.09
    æįħ
    -0.09
    éļĶ
    -0.08
    æIJŃ
    -0.08
    POSITIVE LOGITS
    é¦Ļæ°´
    0.15
    é¦Ļæ°Ķ
    0.13
     smell
    0.12
    é¦Ļåij³
    0.12
    æ°Ķåij³
    0.12
     scent
    0.12
     fragrance
    0.11
    æ°Ķè´¨
    0.11
    é¦Ļ
    0.11
     perfume
    0.10
    Activations Density 0.047%

    No Known Activations