© 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. 30741
    Prev
    Next
    INDEX
    Explanations

    derivative

    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
    ium
    -0.09
    ç§
    -0.08
    纳æĸ¯
    -0.08
     Fet
    -0.08
     gif
    -0.08
    åIJĦ大
    -0.08
    ä¸įèĪį
    -0.08
    è·¨
    -0.08
    å¿ħä¸įåı¯
    -0.08
    ah
    -0.08
    POSITIVE LOGITS
    å¦į
    0.10
    -taking
    0.10
    们
    0.10
    ql
    0.10
    æĸĩç«ł
    0.10
    ooter
    0.09
    ys
    0.09
    vir
    0.09
    ki
    0.09
    ÑĤоп
    0.08
    Activations Density 0.038%

    No Known Activations