© 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. 3494
    Prev
    Next
    INDEX
    Explanations

    comments, reviews, species, users

    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
     trav
    -0.09
    åŀĦ
    -0.08
    åĩºåĵģ
    -0.08
    ãģ«ãģĤãĤĭ
    -0.08
    legs
    -0.08
    Editors
    -0.08
     Babe
    -0.08
    娱
    -0.08
    çļĦæĦıä¹ī
    -0.08
    ç»ĵå°¾
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.14
    太å°ij
    0.10
    å°ıå°ıçļĦ
    0.10
    enburg
    0.10
     sẵ
    0.09
    lessly
    0.09
    InstanceOf
    0.09
    篱
    0.09
    æĴĴ
    0.09
    ukan
    0.08
    Activations Density 0.080%

    No Known Activations