© 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. 1909
    Prev
    Next
    INDEX
    Explanations

    names before was or gave

    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
    ä¼ĹæīĢ
    -0.10
    лен
    -0.09
    бол
    -0.09
    PLAIN
    -0.09
    æ¿Ģ
    -0.08
    éľĩåĬ¨
    -0.08
    ÑĢÑı
    -0.08
    éĽ
    -0.08
    oral
    -0.08
    ç«ĭæ¡Ī
    -0.08
    POSITIVE LOGITS
    ä¼łç»Ł
    0.11
    umas
    0.11
    ç»ıåħ¸çļĦ
    0.10
    -inspired
    0.10
    ç»ıåħ¸
    0.10
    åİĨåı²
    0.09
    thin
    0.09
    鹫
    0.09
    trad
    0.09
    èĢĮçİ°åľ¨
    0.09
    Activations Density 0.143%

    No Known Activations