© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 64038
    Prev
    Next
    INDEX
    Explanations

    price per unit

    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
    Negative Logits
    è¯Ħ
    -0.09
    ought
    -0.09
     Dak
    -0.09
    aza
    -0.08
    ught
    -0.08
    åIJ¸åıĸ
    -0.08
    ä¸Ģèµ·
    -0.07
    pth
    -0.07
    éĢģåİ»
    -0.07
    umo
    -0.07
    POSITIVE LOGITS
    ìĶ©
    0.10
    æ¯ıä½į
    0.10
    uil
    0.10
    è¡Įä¸ļåĨħ
    0.10
    åĩ¡æĺ¯
    0.10
    åĩ¡
    0.10
    éĢĤå½ĵçļĦ
    0.09
    èij©
    0.09
    æ¯ı次
    0.09
    æĢģ度
    0.09
    Activations Density 0.049%

    No Known Activations