© 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. 2721
    Prev
    Next
    INDEX
    Explanations

    booking and reservations

    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
    é¢ijéģĵ
    -0.12
    é£İåij³
    -0.10
    æĮ«
    -0.10
    åį¡è½¦
    -0.09
    æĸ°çīĪ
    -0.09
    _playing
    -0.09
    ç½ijç«Ļåľ°åĽ¾
    -0.09
    éĿĴå°ijå¹´
    -0.09
    çĥģ
    -0.09
    esson
    -0.09
    POSITIVE LOGITS
    æĬ¥åIJį
    0.15
    é¢Ħ约
    0.14
    åIJįé¢Ŀ
    0.13
    é¢Ħ订
    0.12
    æĮĤåı·
    0.11
     RSVP
    0.11
     bookings
    0.10
     booking
    0.10
    é¢Ħå®ļ
    0.10
     booked
    0.10
    Activations Density 0.099%

    No Known Activations