© 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. 34926
    Prev
    Next
    INDEX
    Explanations

    struct array initialization

    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
    ç»ĩ
    -0.08
    åĩĦ
    -0.08
    éĩĬæĶ¾
    -0.08
    åĬĿ
    -0.08
    åĪĨæĪIJ
    -0.08
     DataSet
    -0.08
    èĪįä¸įå¾Ĺ
    -0.08
    京津
    -0.08
    èĪį
    -0.08
    oldemort
    -0.08
    POSITIVE LOGITS
    æĽĻ
    0.10
    çĿģ
    0.10
    溢
    0.10
    ä¸ĢåĪ»
    0.10
    ä¸įäºĨ
    0.09
     полно
    0.09
    è¿ĻæŶåĢĻ
    0.09
    ipa
    0.09
    éŃij
    0.09
     trụ
    0.09
    Activations Density 0.158%

    No Known Activations