© 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. 31061
    Prev
    Next
    INDEX
    Explanations

    average measurement

    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
    家ä¼Ļ
    -0.09
    umpy
    -0.09
    幺
    -0.09
    åħ¬åĬŀ
    -0.09
    iesen
    -0.09
    ä¸į太
    -0.09
    åķ¸
    -0.09
    æľ¬è´¨ä¸Ĭ
    -0.09
     Palace
    -0.08
    _EXIST
    -0.08
    POSITIVE LOGITS
    çī¹çĤ¹æĺ¯
    0.11
    缮çļĦæĺ¯
    0.11
    åİŁåĽłæĺ¯
    0.10
    à¸Ńาย
    0.09
     inventor
    0.09
     estimated
    0.08
    éĩįçİ°
    0.08
    å±Ģéķ¿
    0.08
    æĢ»çļĦ
    0.08
    odia
    0.08
    Activations Density 0.215%

    No Known Activations