© 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. 23088
    Prev
    Next
    INDEX
    Explanations

    event updates and announcements

    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
    éĢIJå¹´
    -0.09
    CTX
    -0.09
    acom
    -0.08
     Hale
    -0.08
    éĥ½ä¸įçŁ¥éģĵ
    -0.08
     ster
    -0.08
    ocal
    -0.08
    è¿Ļ群
    -0.08
    ç½ij讯
    -0.08
    ä¼ģä¸ļæıIJä¾Ľ
    -0.08
    POSITIVE LOGITS
    å½ĵåľº
    0.12
    è¯ŀçĶŁ
    0.11
    çľ¼çķĮ
    0.10
    èªĵè¨Ģ
    0.10
    é¦ĸ次
    0.10
    æĽ´éĩįè¦ģçļĦ
    0.10
    åĪĿæŃ¥
    0.09
    æĦıå¿Ĺ
    0.09
    æĽ´æĸ°
    0.09
    çļĪ
    0.09
    Activations Density 0.158%

    No Known Activations