© 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. 7939
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    ably
    -0.10
    rotch
    -0.10
    ä¸Ģæĸ¹
    -0.09
     NAN
    -0.08
    ableObject
    -0.08
    oux
    -0.08
    лиÑģÑĤ
    -0.08
    æµİ
    -0.08
    ä¸ĢæŶ
    -0.08
    ä¸Ģä¸ĭ
    -0.08
    POSITIVE LOGITS
    æľ¬äºº
    0.10
    äºĽä»Ģä¹Ī
    0.10
    0.09
    æł·çļĦ
    0.09
    çݯçIJĥ
    0.09
    é»į
    0.09
    æİĮéŨ
    0.09
    äºĽ
    0.08
    oes
    0.08
    åѦä¼ļ
    0.08
    Activations Density 0.042%

    No Known Activations