© 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. 3338
    Prev
    Next
    INDEX
    Explanations

    believed to

    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
    éĢ¢
    -0.10
    undef
    -0.09
    æĺİçŁ¥
    -0.09
    zl
    -0.09
    çľĭä»ĸ
    -0.08
     Published
    -0.08
    à¹ģà¸Ĭ
    -0.08
    åIJĮæŶè¿ĺ
    -0.08
    ä¹Łåıªæľī
    -0.08
    çľĭä¼¼
    -0.08
    POSITIVE LOGITS
    eman
    0.09
     бÑĭÑĤÑĮ
    0.09
    槿
    0.09
    è¿ĩå¾Ĺ
    0.09
    çļĦ人æĿ¥è¯´
    0.09
     rap
    0.09
    ÙĪØ®
    0.08
    æĬµ
    0.08
    être
    0.08
    emed
    0.08
    Activations Density 0.148%

    No Known Activations