© 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. 58170
    Prev
    Next
    INDEX
    Explanations

    coffee and espresso

    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
    BED
    -0.09
    åĸĿéħĴ
    -0.09
     Beds
    -0.09
     gaz
    -0.09
    åŀĽ
    -0.09
    åIJĥé¥Ń
    -0.08
    æ¢Ń
    -0.08
    _rom
    -0.08
    udit
    -0.08
    (Edit
    -0.08
    POSITIVE LOGITS
    åĴĸåķ¡
    0.20
     coffee
    0.16
    æĺŁå·´åħĭ
    0.14
    coffee
    0.13
     Coffee
    0.13
     caffeine
    0.13
    ãĤ³ãĥ¼ãĥĴãĥ¼
    0.13
     espresso
    0.12
    âĺķ
    0.12
    Coffee
    0.11
    Activations Density 0.084%

    No Known Activations