© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10221
    Prev
    Next
    INDEX
    Explanations

    state of the art

    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
     Humph
    -0.09
    à¸īà¸ļ
    -0.09
    éĢı
    -0.09
    enade
    -0.09
    墨
    -0.09
    éºĵ
    -0.09
    éĢıéľ²
    -0.09
     повÑĭ
    -0.09
     пÑĢинÑĨип
    -0.09
    è·¯åĨµ
    -0.09
    POSITIVE LOGITS
    MLS
    0.09
    ä¸Ģçŀ¬éĹ´
    0.09
     meanwhile
    0.08
     Ve
    0.08
    æŃ£å¸¸çļĦ
    0.08
    çľĭæĿ¥
    0.08
     hopes
    0.08
     vein
    0.08
    ä¸įåıĹ
    0.08
     midst
    0.08
    Activations Density 0.154%

    No Known Activations