© 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. 10924
    Prev
    Next
    INDEX
    Explanations

    sports leagues and seasons

    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
    çIJ´
    -0.11
    åĸľæ¬¢
    -0.10
    _PROGRAM
    -0.10
    åĩºä¼ļ
    -0.09
    boxing
    -0.09
    ç¨ĭ
    -0.09
    å¯ĵ
    -0.09
    ::.
    -0.09
    å»ºåĽ½
    -0.09
    ç¢ļ
    -0.09
    POSITIVE LOGITS
    ä¸Ń级
    0.11
    顶级
    0.11
    èµĦæł¼
    0.10
    主æµģ
    0.10
    é«ĺçŃī
    0.10
    é«ĺæ¡£
    0.10
    殿åłĤ
    0.10
     mainstream
    0.10
    æĽ´é«ĺ
    0.09
    æݥ轨
    0.09
    Activations Density 0.153%

    No Known Activations