© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50437
    Prev
    Next
    INDEX
    Explanations

    cutting ingredients

    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
    æĮ¥
    -0.11
    contra
    -0.09
    åIJĦçķĮ
    -0.09
    è¿ĩåİ»çļĦ
    -0.09
    ãģĦãģĭ
    -0.09
    slash
    -0.09
    ãģªãģĬ
    -0.09
    ylation
    -0.09
    身ä½ĵåģ¥åº·
    -0.09
     воÑĤ
    -0.08
    POSITIVE LOGITS
    çݳ
    0.08
    æ¶ī
    0.08
    ä½łåĸľæ¬¢
    0.08
    éĹ¹
    0.08
    缨
    0.08
    ochen
    0.07
    ä¿¡æģ¯æľįåĬ¡
    0.07
    ä»İå°ı
    0.07
    orna
    0.07
    æĥ¹
    0.07
    Activations Density 0.002%

    No Known Activations