© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50773
    Prev
    Next
    INDEX
    Explanations

    baseball team names

    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
    天èĬ±
    -0.09
    èįĨå·ŀ
    -0.09
     Henri
    -0.09
    åĽ½åĨħå¸Ĥåľº
    -0.09
    -0.09
    åı¯è¡Į
    -0.09
    转åĬ¨
    -0.08
    .library
    -0.08
    èĬĭ
    -0.08
    踢
    -0.08
    POSITIVE LOGITS
    çĻ£
    0.09
    iative
    0.08
    .Flat
    0.08
     üzerine
    0.08
    ients
    0.08
    èĩªè´¸åĮº
    0.08
     Scouts
    0.08
    pio
    0.08
     @[
    0.08
    ozy
    0.08
    Activations Density 0.014%

    No Known Activations