© 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. 8639
    Prev
    Next
    INDEX
    Explanations

    that would otherwise

    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
    æµĨ
    -0.10
    æľīä¸Ģä½į
    -0.09
     eligible
    -0.09
    çĵ¢
    -0.09
    æĢ»ç®Ĺ
    -0.09
    å½ķçĶ¨
    -0.08
    uitable
    -0.08
     оÑĤлиÑĩа
    -0.08
    çļĦæł·åŃIJ
    -0.08
    èĢĮæĺ¯
    -0.08
    POSITIVE LOGITS
    åIJ¦åĪĻ
    0.16
    åħ¶ä»ĸ人
    0.16
    ä¸ĢèĪ¬äºº
    0.15
    以åīį
    0.15
     otherwise
    0.14
    ä¸įæĽ¾
    0.13
    åīįæīĢæľª
    0.13
    ä¹ĭåīį
    0.13
    otherwise
    0.13
    å¾Īéļ¾
    0.12
    Activations Density 0.088%

    No Known Activations