© 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. 57408
    Prev
    Next
    INDEX
    Explanations

    acknowledging a first time

    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
    åľ¨èģĮ
    -0.10
    楣
    -0.10
    ften
    -0.09
    qua
    -0.09
    è¦ĨçĽĸçİĩ
    -0.09
    诱
    -0.08
    urma
    -0.08
    #line
    -0.08
    è½°
    -0.08
    é¢Ĩ导ä¸ĭ
    -0.08
    POSITIVE LOGITS
    æĤī
    0.11
     vent
    0.10
    vent
    0.09
    VENT
    0.09
    éļ¾å¿ĺ
    0.09
    æĪIJè´¥
    0.09
    ä¹Łæĺ¯ä¸Ģ个
    0.09
     Starr
    0.08
    çļĦ第ä¸Ģ
    0.08
    æ²Ł
    0.08
    Activations Density 0.060%

    No Known Activations