© 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. 23113
    Prev
    Next
    INDEX
    Explanations

    local + noun

    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
     slightest
    -0.09
    park
    -0.09
    æľ¬ç«Ļ
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    è¿Ļ家ä¼Ļ
    -0.09
    æĪIJåijĺåĽ½
    -0.09
    çĢijå¸ĥ
    -0.08
    enia
    -0.08
     kr
    -0.08
    æľ¬ç½ijç«Ļ
    -0.08
    POSITIVE LOGITS
    ities
    0.11
    ä¹ĥèĩ³
    0.11
    abouts
    0.10
    ÑĪек
    0.09
    atel
    0.09
    /global
    0.09
    çļĦä¸ĢäºĽ
    0.09
    èĭ±éĽĦ
    0.09
    èµĸ
    0.09
    IZER
    0.09
    Activations Density 0.020%

    No Known Activations