© 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. 7821
    Prev
    Next
    INDEX
    Explanations

    PlayStation

    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
    ollen
    -0.09
     accred
    -0.09
    unce
    -0.09
    aku
    -0.09
    çļĦåķĨåĵģ
    -0.08
    irez
    -0.08
     tắc
    -0.08
    zens
    -0.08
    ìĨIJ
    -0.08
    _tax
    -0.08
    POSITIVE LOGITS
    aro
    0.10
    çIJĨæĥ³ä¿¡å¿µ
    0.10
    ãģĦãģĨ
    0.09
    aurus
    0.09
    çĽ¸ä¿¡å¤§å®¶
    0.09
    /octet
    0.09
    好çľĭ
    0.09
    ait
    0.09
    æĩĭ
    0.08
     Samoa
    0.08
    Activations Density 0.003%

    No Known Activations