© 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. 39668
    Prev
    Next
    INDEX
    Explanations

    However, may

    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
    æĤĸ
    -0.09
     deb
    -0.09
    edin
    -0.08
    ä¸įéľĢè¦ģ
    -0.08
     bữa
    -0.08
    æ´»çĿĢ
    -0.08
    æ´»ä¸ĭåİ»
    -0.08
    纬
    -0.08
    iful
    -0.07
    presso
    -0.07
    POSITIVE LOGITS
    æ¯ķç«Łæĺ¯
    0.15
    éļ¾åħį
    0.14
    ãģ©ãģĨãģĹãģ¦ãĤĤ
    0.13
    æ¯ķç«Ł
    0.13
     occasionally
    0.12
     иногда
    0.12
    çķ¢ç«Ł
    0.12
    ä¸įåı¯éģ¿åħį
    0.11
    æĢ»ä¼ļ
    0.11
    åģļä¸įåĪ°
    0.11
    Activations Density 0.080%

    No Known Activations