© 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. 20778
    Prev
    Next
    INDEX
    Explanations

    email address

    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
    éĻIJ度
    -0.10
    è¿Ļç¯ĩ
    -0.09
    ä¸ļä½Ļ
    -0.09
     qed
    -0.09
     Caldwell
    -0.08
     бÑĭ
    -0.08
    ä¼¼çļĦ
    -0.08
    çĻĸ
    -0.08
    åĪĿæģĭ
    -0.08
    erties
    -0.08
    POSITIVE LOGITS
    大åħ¨
    0.09
    èIJį
    0.09
     Sax
    0.08
    éĢĹ
    0.08
    DialogTitle
    0.08
     ÑħозÑıйÑģÑĤв
    0.08
    奥巴
    0.08
    éĥ¨èIJ½
    0.08
    äºİæѤ
    0.08
    ess
    0.08
    Activations Density 0.020%

    No Known Activations