© 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. 56693
    Prev
    Next
    INDEX
    Explanations

    quantities, ratios, and measurements

    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
    achievement
    -0.08
     Vog
    -0.08
    èī¯å¥½
    -0.08
     Mund
    -0.08
     ÐŁÐ¾Ñĩем
    -0.08
    cpt
    -0.07
    è¡Ŀ
    -0.07
    ä¸įçŁ¥éģĵ
    -0.07
    æĮģ
    -0.07
    ä¸Ĭä¸ĭ
    -0.07
    POSITIVE LOGITS
    è¿Ļå¥Ĺ
    0.09
    åĽŀäºĭ
    0.09
    çĤ·
    0.09
    forth
    0.08
    ÙĬار
    0.08
    ä¸Ģå¥Ĺ
    0.08
    澧
    0.08
     Washing
    0.08
    üns
    0.08
    è²łè²¬
    0.08
    Activations Density 0.001%

    No Known Activations