© 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. 9843
    Prev
    Next
    INDEX
    Explanations

    vs

    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
    ä¸ĵæłı
    -0.10
    ä¸į容
    -0.10
    为ä¼ģä¸ļ
    -0.09
    åĽŀäºĭ
    -0.09
    åļ¼
    -0.09
    iami
    -0.09
    eel
    -0.09
    æĺ¯ä¸Ģä½į
    -0.08
    æĺ¯ä¸Ģ座
    -0.08
    çªŁ
    -0.08
    POSITIVE LOGITS
    æľ¬èº«
    0.09
    æľ¬èº«çļĦ
    0.09
    èĩªèº«çļĦ
    0.09
    ä½ľèĢħæľ¬äºº
    0.09
    бли
    0.09
    hood
    0.08
    à¸ķà¸Ļà¹Ģà¸Ńà¸ĩ
    0.08
    ãģĿãģĨãģ§
    0.08
    åIJİæĿ¥
    0.08
    ä»ĸ人
    0.08
    Activations Density 0.077%

    No Known Activations