© 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. 640
    Prev
    Next
    INDEX
    Explanations

    all day or night

    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
    åħ¨éĿ¢æİ¨è¿Ľ
    -0.09
    è¿ħéĢŁ
    -0.09
    æĹłéĻIJ
    -0.09
    ç«ĭåį³
    -0.09
    /cms
    -0.09
     Foley
    -0.09
     Chamber
    -0.08
    è¾ĺ
    -0.08
    леÑĤ
    -0.08
    ä¸ĩä¸Ģ
    -0.08
    POSITIVE LOGITS
    以ä¾Ĩ
    0.11
    è·Łä¸įä¸Ĭ
    0.09
    追赶
    0.09
    isin
    0.09
    ago
    0.08
    pped
    0.08
    ÑĤе
    0.08
    侯
    0.08
    è¿Ħ
    0.08
    ente
    0.08
    Activations Density 0.017%

    No Known Activations