© 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. 17052
    Prev
    Next
    INDEX
    Explanations

    life makes things better

    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
    ATAL
    -0.08
     ejac
    -0.08
    æĢ»è§īå¾Ĺ
    -0.08
    é«ĺ强度
    -0.08
    å¤ĸå½¢
    -0.08
    çĮ¥
    -0.08
    عار
    -0.08
    æ¼Ķ
    -0.08
    iste
    -0.08
    æıŃ
    -0.08
    POSITIVE LOGITS
    便åĪ©
    0.10
    ìŀ¥ìĿĦ
    0.09
    åłµ
    0.09
    ä¾¿å®ľ
    0.09
    æĸ¹ä¾¿
    0.09
    ç¼ļ
    0.09
    æĪijä¸įçŁ¥éģĵ
    0.09
    åĺ´å·´
    0.08
     remake
    0.08
    ÑĪÑĥ
    0.08
    Activations Density 0.011%

    No Known Activations