© 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. 55247
    Prev
    Next
    INDEX
    Explanations

    beat the competition or heat

    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
    顺åºĶ
    -0.10
    plib
    -0.09
    ç¬Ķ
    -0.09
    æ¿Ĥ
    -0.08
    rente
    -0.08
    åħ¨éķĩ
    -0.08
    èĬĬ
    -0.08
    åı¸
    -0.08
    agos
    -0.08
    æĢ»èµĦ产
    -0.08
    POSITIVE LOGITS
    iful
    0.09
     beaten
    0.09
    iu
    0.09
     drum
    0.08
     beat
    0.08
    anic
    0.08
    磬
    0.08
    æĮł
    0.08
    ä¸Ģèµ·æĿ¥
    0.08
    饬
    0.08
    Activations Density 0.038%

    No Known Activations