© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21815
    Prev
    Next
    INDEX
    Explanations

    not the only

    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
    æĸ°ä¸Ģè½®
    -0.09
    å·²æĺ¯
    -0.09
    åį³æĺ¯
    -0.09
    оÑĢо
    -0.09
    åħ¨æĺ¯
    -0.09
    ç®Ģ缴æĺ¯
    -0.09
     кÑĢай
    -0.09
    æľīäºĽ
    -0.08
    ads
    -0.08
    太ä¹ħ
    -0.08
    POSITIVE LOGITS
     thing
    0.11
    ones
    0.10
    åĽŀäºĭ
    0.09
    hots
    0.09
    ä¸ĢåĽŀäºĭ
    0.09
    lingen
    0.09
    ä»Ģä¹Īéĥ½
    0.09
    ainers
    0.09
     coisa
    0.09
    æĪijæīį
    0.09
    Activations Density 0.012%

    No Known Activations