© 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. 2028
    Prev
    Next
    INDEX
    Explanations

    way too

    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
    åį´ä¸į
    -0.10
    é¢ĩ为
    -0.10
    ä¸IJ
    -0.09
     má»ĩnh
    -0.09
    éļĻ
    -0.09
     ìĺ¤íŀĪ볤
    -0.09
    èĮ±
    -0.09
    æģ°æģ°
    -0.09
    ctest
    -0.09
    ฯ
    -0.09
    POSITIVE LOGITS
    æ¯ĶåĪ©
    0.10
    ernet
    0.10
    ÑĤов
    0.10
    åľ°ä¸Ń
    0.09
    /ros
    0.08
    linger
    0.08
    å¹´æĿ¥
    0.08
    olver
    0.08
    le
    0.08
    itud
    0.08
    Activations Density 0.008%

    No Known Activations