© 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. 9605
    Prev
    Next
    INDEX
    Explanations

    Latter-Day Saints

    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
    ante
    -0.10
    é¢Ĩçķ¥
    -0.10
    ANTE
    -0.09
    setType
    -0.09
    åIJ¯è¿ª
    -0.09
    EIF
    -0.09
    bon
    -0.08
    ful
    -0.08
    沦
    -0.08
    asso
    -0.08
    POSITIVE LOGITS
    åŀļ
    0.11
    à¹ģà¸Ĺ
    0.11
    ä¸įä¿¡
    0.10
    ism
    0.10
    人家
    0.09
    ischen
    0.09
    opus
    0.09
    изм
    0.09
    ç£ħ
    0.09
    æĹ¥æĬ¥ç¤¾
    0.09
    Activations Density 0.004%

    No Known Activations