© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9156
    Prev
    Next
    INDEX
    Explanations

    of year, month, day, week, century

    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
     TypeName
    -0.10
    ä¸Ģä¸ĭåŃIJå°±
    -0.09
    hus
    -0.08
    /disc
    -0.08
    hic
    -0.08
     Bliss
    -0.08
    éĤ£æł·
    -0.08
     AraÅŁtırma
    -0.08
    æ¹ĥ
    -0.08
    çŃ¹çłģ
    -0.08
    POSITIVE LOGITS
    onus
    0.10
    å¦Ĥæľī
    0.09
    æĻĤãģ¯
    0.09
    olib
    0.08
    èĮ§
    0.08
    æĸ°ä¸ī
    0.08
    è¿ĻäºĽäºº
    0.08
    á»Ń
    0.08
    awan
    0.08
    MBER
    0.08
    Activations Density 0.024%

    No Known Activations