© 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. 48658
    Prev
    Next
    INDEX
    Explanations

    Simpson, Spector, Murphy

    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
    ä¼ŀ
    -0.10
    åı¯æĥ³
    -0.09
    éĽģ
    -0.09
    reet
    -0.08
    åĶ¤
    -0.08
     Jelly
    -0.08
    ä¸Ńå°ıä¼ģä¸ļ
    -0.08
     Hague
    -0.08
    umbing
    -0.08
    llum
    -0.08
    POSITIVE LOGITS
    Ñģел
    0.09
    è¿ĺä¸įæĺ¯
    0.09
     Pry
    0.09
    nier
    0.09
    æĶ¹
    0.08
    æ·¡
    0.08
    åIJIJ
    0.08
    cht
    0.08
    åįĬå²Ľ
    0.08
    åºŀ
    0.08
    Activations Density 0.004%

    No Known Activations