© 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. 2602
    Prev
    Next
    INDEX
    Explanations

    Algeria and Algerian

    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
    纯æ´ģ
    -0.08
    éĴĩ
    -0.08
    çºłæŃ£
    -0.08
    èļ§
    -0.08
    suit
    -0.08
    ය
    -0.08
     заÑĤ
    -0.08
     Gott
    -0.08
    èµ·æĿ¥äºĨ
    -0.08
     Deutsch
    -0.08
    POSITIVE LOGITS
    ennes
    0.10
    ä¸įéĢļ
    0.09
    uien
    0.09
    æĦıæĥ³ä¸įåĪ°
    0.09
    ÑģÑĤан
    0.09
    onaut
    0.09
    erate
    0.09
    Õ¹
    0.09
    åĬ¨èį¡
    0.08
    æ·¡åĮĸ
    0.08
    Activations Density 0.015%

    No Known Activations