© 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. 11360
    Prev
    Next
    INDEX
    Explanations

    names followed by punctuation/conjunctions

    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
    缴æݥ影åĵį
    -0.10
     Clarkson
    -0.09
    soever
    -0.09
    رص
    -0.09
    å°ıå·§
    -0.09
    æݸ
    -0.09
    åIJij社ä¼ļ
    -0.08
    æĮ¤
    -0.08
    æĵł
    -0.08
    å¿«æĬ¥
    -0.08
    POSITIVE LOGITS
    éļ§
    0.13
    PUR
    0.09
    пиÑĤ
    0.09
    OWN
    0.08
    à¸ļำร
    0.08
    azar
    0.08
    arie
    0.08
     Locked
    0.08
    ä¸Ģè½®
    0.08
    wers
    0.08
    Activations Density 0.008%

    No Known Activations