© 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. 33346
    Prev
    Next
    INDEX
    Explanations

    made it

    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
    æ¾İ
    -0.10
    çĽĤ
    -0.09
    tras
    -0.09
    ÑĢен
    -0.09
    idos
    -0.09
    åŀ£
    -0.09
    éĻ·
    -0.09
    tern
    -0.08
    mun
    -0.08
    _STRUCTURE
    -0.08
    POSITIVE LOGITS
    便æĺ¯
    0.09
    åºĶ该æĺ¯
    0.08
    çļĦæĹ¥åŃIJ
    0.08
    çļĦå°±æĺ¯
    0.08
    çļĦæĦıä¹ī
    0.08
    ä¾Ŀ次
    0.08
    sz
    0.08
    çļĦç¡®æĺ¯
    0.08
    好ä¸į好
    0.08
    æĽ´å¤ļçļĦæĺ¯
    0.08
    Activations Density 0.004%

    No Known Activations