© 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. 3838
    Prev
    Next
    INDEX
    Explanations

    South Shore, South Bay, South China

    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
    èĸĦå¼±
    -0.10
    éļĹ
    -0.09
    çĸ¤
    -0.09
    åľ¨ç½ij绾ä¸Ĭ
    -0.08
     spec
    -0.08
    æĵį
    -0.08
    _specs
    -0.08
    haul
    -0.08
    è¿ľè¿ľ
    -0.08
    aser
    -0.08
    POSITIVE LOGITS
     eÄŁer
    0.09
    =~
    0.09
    æĺ¯åĽ½åĨħ
    0.09
    人家
    0.09
    仿
    0.09
    odox
    0.09
    çļĦæľ¬è´¨
    0.08
    ãģ¹
    0.08
    æľ¬è´¨
    0.08
    åIJĦè¡Į
    0.08
    Activations Density 0.094%

    No Known Activations