© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37300
    Prev
    Next
    INDEX
    Explanations

    preposition followed by sports league

    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
    Nom
    -0.11
     Convers
    -0.10
    aption
    -0.09
    ä¸Ģ个æĺ¯
    -0.09
     Nom
    -0.09
    大家åĪĨ享
    -0.09
    åĩłåIJį
    -0.09
    åĽ½æ°ijç»ıæµİ
    -0.09
    ä¸įå¾Ĺ转载
    -0.09
    ÙĦÙĤ
    -0.08
    POSITIVE LOGITS
    ä¸ĭæīĭ
    0.08
    ä¸ĸéĹ´
    0.08
     Geb
    0.08
    Towards
    0.08
    æ°ĶåĬ¿
    0.08
    å¦ĸæĢª
    0.08
    ä¸įå½±åĵį
    0.08
    _Enter
    0.07
     cudd
    0.07
    world
    0.07
    Activations Density 0.016%

    No Known Activations