© 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. 58814
    Prev
    Next
    INDEX
    Explanations

    weekdays and days

    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
     chatt
    -0.10
    以èī²
    -0.09
    пиÑģ
    -0.09
    ä½łä»¥ä¸º
    -0.08
    ä¸ĢåĽ¢
    -0.08
    ÙĦع
    -0.08
    çĵ®
    -0.08
    عداد
    -0.08
    è¨ĺå¾Ĺ
    -0.08
    ä»Ģ麽
    -0.08
    POSITIVE LOGITS
    utom
    0.09
    æĹ¥åľ¨
    0.09
    inals
    0.08
    ãĥ³ãĤ°
    0.08
    ussion
    0.08
    dden
    0.08
    ä¸įä¸Ĭ
    0.08
    uters
    0.08
    thed
    0.08
    izer
    0.08
    Activations Density 0.005%

    No Known Activations