© 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. 34765
    Prev
    Next
    INDEX
    Explanations

    it seems that

    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
    its
    -0.09
    è¿ĽèĢĮ
    -0.09
    ä¸Ģ樣
    -0.08
    ä¸Ģçľĭ
    -0.08
    没äºĭ
    -0.08
     ÑģебÑı
    -0.08
     поиÑģк
    -0.08
    맨
    -0.08
    人æµģ
    -0.08
    æľīä¿¡å¿ĥ
    -0.08
    POSITIVE LOGITS
    ä¸İæŶ
    0.10
    ansen
    0.10
    utan
    0.09
    æĪIJè´¥
    0.08
    lor
    0.08
    ä¸ĵ
    0.08
    Parms
    0.08
    ä¸ĭçļĦ
    0.08
     bask
    0.08
    åľ¨è¿Ļ个
    0.08
    Activations Density 0.056%

    No Known Activations