© 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. 30823
    Prev
    Next
    INDEX
    Explanations

    Silverlight, SharePoint, Liferay, collections, Kanye West

    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
    nap
    -0.09
    åĴĮåľ°åĮº
    -0.09
    ãģ¤ãģį
    -0.09
     그리
    -0.09
    izr
    -0.09
     ведÑĮ
    -0.08
    à¸ģระà¸Ĺ
    -0.08
    ampler
    -0.08
    stitute
    -0.08
     nhắc
    -0.08
    POSITIVE LOGITS
    arge
    0.11
     Sche
    0.09
    èĥ½å¾ĹåĪ°
    0.09
    ofile
    0.09
    åīįä¸ĸ
    0.09
    /us
    0.09
    unch
    0.09
    ä¸ĸ家
    0.08
    cÃŃ
    0.08
    ä¸Ģåįĥ
    0.08
    Activations Density 0.043%

    No Known Activations