© 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. 30707
    Prev
    Next
    INDEX
    Explanations

    team names and sports actions

    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
    lass
    -0.09
    éķ¿è¾Ī
    -0.08
    å½ĵåľº
    -0.08
    åĨħå¿ĥçļĦ
    -0.08
    å«Į
    -0.08
    .trip
    -0.08
     Catholic
    -0.08
    é¢Ĭ
    -0.08
    aky
    -0.08
    è¡Įä¸ļçļĦ
    -0.08
    POSITIVE LOGITS
    篦
    0.09
    åķĦ
    0.09
    æĪ´
    0.09
    æĤ¬
    0.09
    à¹Į
    0.08
    ifact
    0.08
    ibox
    0.08
    istration
    0.08
    åİ¿åŁİ
    0.08
    çŀ¢
    0.08
    Activations Density 0.005%

    No Known Activations