© 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. 1314
    Prev
    Next
    INDEX
    Explanations

    playoff season division title

    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
    就读
    -0.10
    æĪIJ为ä¸ĢåIJį
    -0.10
    大æī¹
    -0.10
     Leone
    -0.10
    èĢĥä¸Ĭ
    -0.09
    èĮĤ
    -0.09
    åĪ°åľº
    -0.09
    æĺİæĺŁ
    -0.09
     Morr
    -0.09
    ä¼ļéĢłæĪIJ
    -0.09
    POSITIVE LOGITS
    è¯ļæĦı
    0.10
    å¹´æľ«
    0.09
    å¸Į
    0.09
    tero
    0.09
    æŃĩ
    0.09
    ç»Ń
    0.08
    çĸĶ
    0.08
    å¦ĤæľŁ
    0.08
    âĨĹ
    0.08
     Dünya
    0.08
    Activations Density 0.135%

    No Known Activations