© 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. 57191
    Prev
    Next
    INDEX
    Explanations

    suitable for opportunities

    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
     è¾
    -0.10
    ulty
    -0.09
    ä¹ŁçŁ¥éģĵ
    -0.09
    åĩĮ
    -0.08
    ye
    -0.08
    ofile
    -0.08
    تعÙĦÙĬÙħ
    -0.08
    gué
    -0.08
     ÙĪبÙĬÙĨ
    -0.08
    нÑİ
    -0.08
    POSITIVE LOGITS
    æľºä¼ļ
    0.12
    æľīæľºä¼ļ
    0.11
     oportun
    0.10
    çĸµ
    0.10
    çļĦæľºä¼ļ
    0.10
    æ©Łæľĥ
    0.10
     opportunity
    0.10
    çļĦåIJĪä½ľ
    0.09
     ripe
    0.09
    åIJĪä½ľ
    0.09
    Activations Density 0.058%

    No Known Activations