© 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. 55797
    Prev
    Next
    INDEX
    Explanations

    all, everything, in one

    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
    otron
    -0.11
    èĮĦ
    -0.11
    ä¸įè´Ł
    -0.10
    ValuePair
    -0.10
    å½¼
    -0.09
    Ñĥз
    -0.09
    éĩijèŀįå¸Ĥåľº
    -0.09
    åѦä¼ļ
    -0.09
    æĭ£
    -0.09
    nil
    -0.08
    POSITIVE LOGITS
    åľ¨åIJĮä¸Ģ
    0.14
    äºİä¸Ģä½ĵ
    0.14
    为ä¸Ģä½ĵçļĦ
    0.14
    åIJĮä¸Ģ
    0.13
    ä¸Ģä½ĵåĮĸ
    0.13
    ä¸ĢæĿ¡é¾Ļ
    0.12
    éĥ½åľ¨
    0.12
    ä¸Ģç«Ļå¼ı
    0.12
    ä¸Ģä½ĵ
    0.12
    äºİä¸Ģä½ĵçļĦ
    0.11
    Activations Density 0.132%

    No Known Activations